Object Color Research Articles

246 Evaluation of Live Growth Performance and Carcass Characteristics of Late Finishing Phase Beef Cattle with Varying Degrees of Pulmonary Hypertension

Abstract Late feedlot death caused by congestive heart failure has been quantified extensively through epidemiological studies however, these models do not consider losses or gains associated live growth performance, carcass quality, and consumer rejection of meat products. To address these gaps in the literature, we conducted two studies to characterize effects of pulmonary hypertension on four populations of feedlot cattle. In study one, reproductively intact (INT, n = 19), and ovariectomized (OVX, n = 18) yearling Sim-Angus heifers were selected on heart failure risk according to their pulmonary arterial pressure. Heifers were gradually transitioned onto a feedlot ration and fed to an acceptable harvest body composition determined using both 12th rib subcutaneous fat and body weight. Cattle were weighed biweekly and ADG was calculated by regressing body weight by days on feed (DOF). Pulmonary arterial pressure (PAP) was measured approximately every 3 months by a qualified veterinarian. Cattle were harvested at a commercial harvesting facility where carcass data and muscle samples were collected. In study two, weaned sim-angus steers (n = 41) were selected on heart failure risk categories using the same methodology outline above. Twenty steers were administered a steroidal growth promoting implant upon receiving (IMP) and twenty were untreated (NAT). Steers were fed to an average of 610 kg and data were collected using the same methodology outlined above. Data were analyzed using ANOVA, linear model, and Pearson correlation functions in R statistical software where PAP was used as a fixed continuous variable. Data were analyzed by study with the exception of live growth performance regression and correlations where data were combined. Linear regression within the combined datasets showed that initial mean PAP (P < 0.001), diastolic pressure (P < 0.001), and sex (P < 0.001) positively influenced ADG throughout the duration of the finishing period. Furthermore, initial PAP was moderately correlated with ADG (R = 0.38, P < 0.001). Gain to feed (G:F) was positively correlated with initial diastolic PAP (R = 0.31, P < 0.006). Neither initial mean PAP nor diastolic pressures impacted dry matter intake (DMI; P > 0.90), but sex was associated with DMI where steers had significantly decreased DMI (P = 0.003). Within study two, longissimus muscle objective color values were influenced by PAP where a* (redness; P < 0.001) and b* (yellowness; P < 0.04) values were negatively correlated with final PAP. These data begin to demonstrate the close relationship between live growth performance and pulmonary hypertension. More research is needed to better understand how cellular energy metabolism is potentially contributing to increased growth performance but negatively influencing muscle health in the form of oxygen binding capacity and inflammation.

Compositional properties of planet-crossing asteroids from astronomical surveys

Context. The study of planet-crossing asteroids is of both practical and fundamental importance. As they are closer than asteroids in the Main Belt, we have access to a smaller size range, and this population frequently impacts planetary surfaces and can pose a threat to life. Aims. We aim to characterize the compositions of a large corpus of planet-crossing asteroids and to study how these compositions are related to orbital and physical parameters. Methods. We gathered publicly available visible colors of near-Earth objects (NEOs) from the Sloan Digital Sky Survey (SDSS) and SkyMapper surveys. We also computed SDSS-compatible colors from reflectance spectra of the Gaia mission and a compilation of ground-based observations. We determined the taxonomy of each NEO from its colors and studied the distribution of the taxonomic classes and spectral slope against the orbital parameters and diameter. Results. We provide updated photometry for 470 NEOs from the SDSS, and taxonomic classification of 7401 NEOs. We classify 42 NEOs that are mission-accessible, including six of the seven flyby candidates of the ESA Hera mission. We confirm the perihelion dependence of spectral slope among S-type NEOs, likely related to a rejuvenation mechanism linked with thermal fatigue. We also confirm the clustering of A-type NEOs around 1.5–2 AU, and predict the taxonomic distribution of small asteroids in the NEO source regions in the Main Belt.

Robot Untuk Mendeteksi Objek dengan Citra Digital dan Notifikasi Short Message Service (SMS)

The use of the camera can only be used as a monitor which is usually used not equipped with other devices that allow it to hit an object, be it a human or an object and by using a camera is a hardware device that functions to capture images and convert them into digital images that can be read and processed. by a computer using a robot controlled by a smartphone in approaching objects, the camera sensor is useful for detecting colored ball objects. The detected colors consist of Red, Green, Blue, all colors are processed in the microcontroller which functions as the brain of the robot that is made and later the robot will send information in the form of SMS the results of color objects that have been detected. Research results On the camera sensor, the larger the megapixel camera used, the clearer the resulting image will be in the detection process. The time for sending SMS to the destination number is based on the signal quality of the GSM provider used and in developing information, real-time object information can be added. for object detection will be displayed directly by the smartphone connected to the robot.

Management of Melasma through <i>Ayurveda</i> – A Case Report

Melasma is a pigmentary disorder hyperpigmentation primarily occurring on the cheeks, forehead, and bridge on the nose, upper lip, and occasionally elsewhere on the face. It is painless, superficial brownish macular patches. Modern science recommends laser therapy and various types of steroid use for treating melasma. Laser therapy is very expensive, and steroids have many side effects. So, in this study management of melasma has been done through Ayurveda, which is cost-effective, and easily available with the least side effects. From the signs and symptoms, melasma looks identical to Vyanga as per Ayurvedic texts that come under Kshudraroga (minor disease). In Ayurveda, external therapy Lepa (local application), is prescribed as one of the therapeutic measures for effectively managing melasma. A 32-year-old female patient was diagnosed clinically with melasma. She got treatment from a dermatologist and applied an allopathic care cream over the brownish patches. After regular application of the cream, a brownish patch does not decrease. She has no history of sunray exposure and has no family history. So, she went to Ayurvedic treatment. She was treated with Ayurvedic Lepa for local application and Panchanimbadi Churna internally for 21 days. The content of Ayurvedic Lepa was Nutmeg (Myristica fragrans Houtt.) Churna (powder), and Dugdha (milk). In ancient science, Nutmeg is known by the name of Jatiphala. Nutmeg is a very useful drug utilized therapeutically, and spice and Panchanimbadi are useful in all types of Raktavikara (blood disorders). The result was assessed with subjective and objective parameters, i.e., colour score and MASI score. After 21 days of treatment, significant changes were observed without any side effects. The colour score decreases from 3 to 1, and the MASI score from 15.2 to 10.1.

194 A Systems Approach to Deriving Carcass Value from Holstein x Simangus Cattle in an Accelerated Finishing Model

Abstract Crossbreeding dairy cows with beef sires has increased in the U.S. dairy industry. This beef x dairy mating results in dairy-beef which has altered the U.S. fed beef supply. The predominant mating has been Holstein x Angus, thus research was conducted to determine the effects of Holstein x SimAngus breeding on growth performance, carcass characteristics, and fresh meat quality. Starting on d 1, Holstein steers (n = 9) and Holstein x SimAngus (HolSim) steers (n = 12) were fed once daily at 0830 h, until an end weight of 635 kg was reached. Holstein steers averaged 421 d and HolSim steers averaged 432 days on feed. Daily feed offered was delivered into a semi-autonomous feed monitoring system designed to measure individual animal intake and feeding behavior (GrowSafe System Ltd). Steer body weight was recorded every 28 d. Data collected were used to calculate dry matter intake (DMI), average daily gain (ADG), and gain to feed ratio (G:F). Steers were humanely slaughtered under USDA inspection, immediately following slaughter hot carcass weight (HCW) was recorded and 48 h following slaughter, carcass length, body width, backfat thickness and area of the longissimus muscle (LM) was recorded. Strip loins were collected from each carcass and aged for 14 d. After aging, Warner-Bratzler shear force (WBSF) and slice shear force (SSF) were determined. Remaining steaks were placed under retail display for 7 d. Objective color was measured after 0, 1, 3, 5, and 7 d in retail display. No differences were observed for ADG and G:F between Holstein and HolSim steers (P > 0.05). A tendency was observed for Holstein steers to have a greater DMI compared with HolSim steers (P = 0.0646). The HolSim steers had greater HCW and dressing percentages compared with Holstein steers (P < 0.0001). The HolSim carcasses had shorter carcass lengths and body widths compared with Holstein carcasses (P = 0.0005). Holstein carcasses had less backfat compared with HolSim carcasses (P = 0.0034). The LM area was larger in HolSim carcasses (P < 0.0001). No differences were observed for WBSF or SSF (P > 0.05). Strip steaks from HolSim steers had less deoxymyoglobin and greater oxymyoglobin values on d 0 of retail (P < 0.05). Strip steaks from HolSim steers had greater a* and saturation index values on d 7 in retail (P < 0.05). Strip steaks from HolSim steers had decreased metmyoglobin values and greater oxymyoglobin values on d 7 in retail (P < 0.05). Thus, indicating strip steaks from HolSim steers had increased red color. Growth performance data in this study confirm previous literature reported when comparing dairy x dairy to beef x dairy steers. Carcass and fresh meat data suggest that Holstein x SimAngus steers had improved yield production compared with Holstein steers without a loss in quality when steers were fed to a weight constant end point.

Exploiting sublimated deep features for image retrieval

Deep learning techniques can be used to describe image content, which is a good way to reduce the semantic gap between low-level and high-level features. However, convolutional neural networks (CNNs) exhibit texture bias and largely ignore global object shape. This does not conform to human perception and can fail to gain the advantages of both low-level features and deep features. To address this problem, in this work, the main focus was shifted from using simple deep features to the use of sublimated deep features, which incorporate global object shape and color features. Along these lines, in this work, a novel image retrieval method named the sublimated deep feature histogram (SDFH) was proposed. The main highlights are: 1) An effect orientation feature was introduced, namely, orientation-selective feature, to mimic the orientation-selection mechanism. This provides a good representation of global object shape and reduces the side-effects of texture bias. 2) A new concept was developed, namely color perceptual feature, to address the shortcoming of deep features—that they discard color features. This includes color cues in the deep features and provides a more discriminating representation. 3) The orientation selective and color perception mechanisms were effectively mimicked to provide a compact yet efficient representation, and propose an effective transfer learning method called gain whitening learning. By carrying out comparative experiments, it was demonstrated that sublimated deep features can provide highly competitive retrieval performance (in terms of mean average precision) using a pre-trained CNN model applied to well-known benchmark datasets. Our results provide new insights into image retrieval based on the mechanisms of the primary visual cortex (V1). Furthermore, the method is more in line with human perception than other methods.

Visual mental imagery of atypical color objects attracts attention to an imagery-matching object.

Mental imagery attracts attention to imagery-matching stimuli. However, it remains unknown whether voluntarily imagined atypical color also attracts attention to a stimulus that matches the imagery when the imagined stimuli are color-diagnostic objects, which are strongly associated with typical color. This study investigated whether people can voluntarily imagine atypical colors of such objects and attend to imagery-matching stimuli. Participants in the imagery group were instructed to imagine an atypical color of the black-white objects according to the instructed color or voluntarily selected color, whereas participants in the control group were instructed to attend to the objects without any instruction of imagery. Thereafter, they detected a color target in a visual search task. Results revealed that participants in the imagery group directed attention to the imagery-matching atypical color, not to the original color of the object in the search. Meanwhile, participants in the control group did not demonstrate any attentional guidance. These results suggest that voluntarily imagining atypical color can attenuate mental representations of the original color imagery and change attention to a stimulus that matches imagery.

Brain tumour MRI detection and classification based on the convolutional neural network

Magnetic Resonance Imaging (MRI) has emerged as a widely used diagnostic technique for brain tumour detection. However, the diagnosis of brain tumours poses significant challenges due to their occurrence in diverse locations and various types. Furthermore, MRI generates images that require manual analysis by physicians, which can be laborious and prone to errors. To enhance the efficacy and accuracy of brain tumour detection, recent advances in artificial intelligence have led to the development of machine learning algorithms. In this study, a convolutional neural network (CNN) based method was proposed for brain tumour detection and classification through the preprocessing of raw MRI images. The customized CNN model achieves an accuracy of 98% on a dataset consisting of four types of MRI images, including three types of brain tumours and healthy brain images, with preprocessing applied to all images. The CNN model demonstrates an accuracy of 95% in classifying raw MRI images from the dataset. The CNN model's performance is further improved by training the model with preprocessed images that have been transformed into the same colour space and object area zoomed in. These findings provide a promising avenue for the development of automated and efficient brain tumour detection systems using CNN and MRI.

Memory colors of familiar objects induce general color preference

AbstractPrevious studies have offered multiple explanations for the causality of color preference but no consensus has been reached. In this study, we propose an alternative explanation that the memory colors of familiar objects, especially food colors of humans can induce color preferences. We conducted two experiments. In Experiment 1, the memory color experiment, we asked participants to rate the similarity between presented color samples and memory colors of five familiar fruits and vegetables in Japan; we then calculated the location of the colors in the CIELAB color space that looked most similar to the remembered objects using the bivariate Gaussian function. In Experiment 2, the color preference experiment, color variations were created based on the memory colors obtained from Experiment 1. A different group of participants rated their preference for each color variation, then we applied regression analysis to these ratings. We observed two types of regressions between preference ratings and distance to memory colors: (1) for colors from red to green that represent the food colors for primates, color preference increased when the color was closer to the memory colors of the fruits and vegetables found in Experiment 1; and (2) for blue and purple colors, colors were preferred when they became bluer. We suggest that the evolutionarily acquired mechanism of color preference derives crucial cues from our ecological environment. Therefore, the mechanism produces the same color preference trend among people who grow up in similar environments, for example, environments containing the same fruits.

Emergency Floor Plan Digitization Using Machine Learning.

An increasing number of special-use and high-rise buildings have presented challenges for efficient evacuations, particularly in fire emergencies. At the same time, however, the use of autonomous vehicles within indoor environments has received only limited attention for emergency scenarios. To address these issues, we developed a method that classifies emergency symbols and determines their location on emergency floor plans. The method incorporates color filtering, clustering and object detection techniques to extract walls, which were used in combination to generate clean, digitized plans. By integrating the geometric and semantic data digitized with our method, existing building information modeling (BIM) based evacuation tools can be enhanced, improving their capabilities for path planning and decision making. We collected a dataset of 403 German emergency floor plans and created a synthetic dataset comprising 5000 plans. Both datasets were used to train two distinct faster region-based convolutional neural networks (Faster R-CNNs). The models were evaluated and compared using 83 floor plan images. The results show that the synthetic model outperformed the standard model for rare symbols, correctly identifying symbol classes that were not detected by the standard model. The presented framework offers a valuable tool for digitizing emergency floor plans and enhancing digital evacuation applications.

Fluorescent whiteness measurement of textiles by multispectral imaging system

AbstractAccurate whiteness measurement is critical across various industries including textiles, paper, and detergents. With the advent of fluorescent whitening agents (FWAs), the assessment of whiteness has evolved from simply measuring reflectance to determining the spectral radiance factor (SRF) of materials. While multispectral imaging (MSI) can effectively measure object reflectance and colour, its accuracy is compromised by FWAs that significantly augment spectral reflectance. Thus, reliable whiteness measurement requires the determination of both reflectance and SRF. This article presents the design of a specialised light source equipped with an ultraviolet (UV) filter to provide adjustable illumination within an integrating sphere system. By tuning the position of the UV filter, multispectral images are captured of a fabric under varying UV exposures. These images are subsequently processed and combined to reconstruct full‐range visible spectrum information. This approach is shown to achieve high accuracy and spatial uniformity in quantifying the whiteness of textiles using MSI.

Organoleptic Study of Dumbo Catfish Sausage (Clarias Gariepinus) With Carrot ( Daucus Carota,L ) And Mocaf Flour Substitution

African catfish is an easy fish cultivated, no requires large capital as well as its growth fast, unfortunately consume catfish in form processed Still limited so that need processed become sausage. Sausages that use material 100 % raw catfish meat produce lacking product well, that is colored white grayish and has a rancid aroma so that not enough liked. For That need added carrot with objective increase quality color, minimizes rancid aroma and improves mark nutrition. Study This aim know level favorite panelist to Dumbo catfish sausage with substitution treatment carrots and Mocaf. Design study use Completely Randomized Design with 1 factor that is substitution Mocaf and carrots with comparison: P1 (Mocaf 5% carrot 35%), P2 (Mocaf 10% carrot 30%), P3 ( Mocaf 15% carrot 25%) and P4 ( Mocaf 20% carrot 20%) from heavy material catfish meat .Every treatment tested in a way organoleptic against 30 panelists covers texture, aroma, taste and color on a scale of 1-5. Collected data analyzed with analysis variance and if there is difference next with the BNT (Significant Difference) test Smallest) at level significance 5%. Research results show treatments P1, P2, and P3 did not different real and real preferred treatment panelist based on the parameters of texture (average score 3.94-4.23), aroma (average score 3.61-3.94), taste (average score 3.76-4.03) and color (average score 3.75-4.09).

IOT COLOR BASED PRODUCT SORTING MACHINE

The IoT Color-Based Product Sorting Machine is a cutting-edge automated system designed to revolutionize the manufacturing and packaging industries. This innovative solution employs Internet of Things (IoT) technology to enable efficient and precise sorting of products based on their color attributes. The system integrates advanced image recognition algorithms, sensor networks, and cloud computing to streamline the sorting process. Color Based Object Sorting has a wide usage in fruit sorting as well as candy sorting industries. This system puts forward a mechanism to detect color and sort items through image processing. Once identified a mechanism is used to sort the candies into particular bins baskets. We here demonstrate this mechanism using a camera with electronic circuitry along with sorting mechanism using 3 bins. The system uses raspberry pi connected to a controller circuit to achieve this task. The controller circuit consists of a camera attached to it that detects color of a small object in front of it. A motor is used to feed an object to the camera chamber. As soon is the color is detected a signal is sent to the sorter mechanism which uses a motor to position the sorting tube towards respective section. A feeder is then used to push the object towards the tubs so that it gets sorted and next object is pulled in by the feeder. The action details are sent to the IOT server using iotgecko platform to keep track of the number of objects sorted in each section. Thus we achieve a completely automated IOT based sorting system.Color based product sorting has a wide usagein fruits sorting as well as candy sorting industries. Now a day’s industrial area requires demand for automation. Due to automation human efforts are goes on decreasing day-byday. Since last decade .This system puts forward mechanism to detect color and sort item through image processing. This mechanism is used to sort the candies into particular bins or baskets Key Words: IoT, colour sensor, servo motor, node MCU,,

A semiotic intertextual analysis of beauty influencers' communication strategies on youtube: uncovering meaning and influence by using Pierce's framework

This research aims to conduct a semiotic intertextual analysis of beauty influencers on YouTube. Specifically, the study centers on two prominent beauty influencers, Andra Alodita, and Kornelia Meilinda, and their strategies for effectively promoting recommended lipstick products. The research was conducted employing a qualitative approach, utilizing Peirce's semiotic theory. The findings reveal that beauty influencers strategically employ visual elements to convey meaning and captivate viewers' attention. Both Andra Alodita and Kornelia Meilinda meticulously craft their content, considering factors such as color schemes, backgrounds, and object placement. They adopt distinct approaches to reviewing lipstick products tailored to diverse audiences and preferences. This multiplicity of perspectives enhances the complexity of semiotic elements within beauty influencer content and broadens the spectrum of meanings conveyed to viewers. Furthermore, the findings underscore the significance of semiotic intertextuality as a potent tool for beauty influencers to shape meaning, influence perceptions, and resonate with their extensive audience. These findings offer valuable insights for marketers, brands, and content creators seeking to leverage semiotics' potential in shaping beauty trends and consumer behavior.

Characterization of Objective Skin Color Changes during and after Breast and Chest Wall Radiotherapy and Correlation with Radiation-Induced Skin Toxicity in Breast Cancer Patients, Including Patients with Skin of Color

Radiation dermatitis (RD) is common among women undergoing breast and chest wall radiotherapy (RT); however, existing scales to assess the severity of RD are subjective and do not account for variability in skin of color (SOC). For instance, the Common Terminology Criteria for Adverse Events (CTCAE) criteria do not include hyperpigmentation in the grading scale. There is data indicating worse RD in African American and Hispanic patients; however, the rate and severity in SOC remains unknown given the lack of data using objective measures of RD. Spectrophotometry is one method to quantify the appearance of color by measuring spectral characteristics without the bias associated with subjective clinical scoring. We present a phase I prospective non-therapeutic clinical trial to objectively define SOC at baseline and evaluate spectrophotometric skin changes during and after breast or chest wall RT in parallel with physician-graded RD using CTCAE criteria. We hypothesize that there will be greater discrepancy between physician graded RD and objective measures of RD in patients with SOC in whom hyperpigmentation will be undercaptured by physician-grading. This is the first study intending to correlate SOC with objective changes after RT as a reliable indicator of RD. We offer a novel system for evaluating RD that is applicable to SOC. A total of 60 patients with localized breast cancer (stage 0-III) undergoing conventional whole breast or chest wall RT (50Gy/ 25 fx), hypofractionated whole breast RT (40.5Gy/15 fx) or ultrahypofractionated partial breast RT (6Gy x5), with or without regional nodal RT were enrolled. 3 skin color readouts using the Commission International de l'Eclairage 3D color system (l*, a*, b*) were measured within the radiation field using a spectrophotometer at baseline, once weekly during RT, 10 days post RT, 4 weeks and 12 months post RT. The spectrophotometer is a non-invasive, hand-held device that is used in the clinic room with no additional equipment or setup requirements. Data is automatically exported to a spreadsheet organized by timepoint and patient. The l* axis is a gray scale (0 = black, 100 = white) correlating with skin pigmentation and the a* axis describes red and green values correlating with erythema. The primary objective is to evaluate the changes from baseline in skin color readouts in the quadrant of tumor location during and after RT based on fractionation. The secondary objective is to evaluate changes within and across groups defined by baseline skin color. Exploratory objectives include evaluating the association of baseline color readouts and changes after RT with acute and late grade > 2 clinician-rated skin and subcutaneous tissue effects according to the CTCAE, v5.0, physician graded cosmesis and clinical interventions to treat RD, such as use of topical steroids and oral analgesics. As of January 2023, we have enrolled 100% of the planned patients. To be determined. To be determined. Clinical Study Identifier: S22-00192.

MODAN: Multifocal Object Detection Associative Network for Maritime Horizon Surveillance

In maritime surveillance systems, object detection plays a crucial role in ensuring the security of nearby waters by tracking the movement of various objects, such as ships and aircrafts, that are found at sea, detecting illegal activities and preemptively countering or predicting potential risks. Using vision sensors such as cameras to monitor the sea can help to identify the shape, size, and color of objects, enabling the precise analysis of maritime situations. Additionally, vision sensors can monitor or track small ships that may escape radar detection. However, objects located at considerable distances from vision sensors have low resolution and are small in size, rendering their detection difficult. This paper proposes a multifocal object detection associative network (MODAN) to overcome these vulnerabilities and provide stable maritime surveillance. First, it searches for the horizon using color quantization based on K-means; then, it selects and partitions the region of interest (ROI) around the horizon using the ROI selector. The original image and ROI image, converted to high resolution through the Super-Resolution Convolutional Neural Network (SRCNN), are then passed to the near-field and far-field detectors, respectively, for object detection. The weighted box fusion removes duplicate detected objects and estimates the optimal object. The proposed network is more stable and efficient in detecting distant objects than existing single-object detection models. Through performance evaluations, the proposed network exhibited an average precision surpassing that of the existing single-object detection models by more than 7%, and the false detection rate was reduced by 59% compared to similar multifocal-based state-of-the-art detection methods.

Long-term memory for distractors: Effects of involuntary attention from working memory.

In a visual search task, attention to task-irrelevant distractors impedes search performance. However, is it maladaptive to future performance? Here, I showed that attended distractors in a visual search task were better remembered in long-term memory (LTM) in the subsequent surprise recognition task than non-attended distractors. In four experiments, participants performed a visual search task using real-world objects of a single color. They encoded color in working memory (WM) during the task; because each object had a different color, participants directed their attention to the WM-matching colored distractor. Then, in the surprise recognition task, participants were required to indicate whether an object had been shown in the earlier visual search task, regardless of its color. The results showed that attended distractors were remembered better in LTM than non-attended distractors (Experiments 1 and 2). Moreover, the more participants directed their attention to distractors, the better they explicitly remembered them. Participants did not explicitly remember the color of the attended distractors (Experiment 3) but remembered integrated information with object and color (Experiment 4). When the color of the distractors in the recognition task was mismatched with the color in the visual search task, LTM decreased compared to color-matching distractors. These results suggest that attention to distractors impairs search for a target but is helpful in remembering distractors in LTM. When task-irrelevant distractors become task-relevant information in the future, their attention becomes beneficial.

Temporal-agnostic change region proposal for semantic change detection

Remote sensing imagery allows temporal and large-scale observation of the Earth, and advanced techniques such as deep learning have been developed to deal with the massive data. As a result, by combining remote sensing with deep learning, it is possible to realize change detection, which can reveal the change in land cover and land use. Recent work has focused on semantic change detection (SCD), which simultaneously locates where the changes took place while identifying what objects changed between the different periods. Deep learning based SCD methods are typically based on a multi-task structure, which combines the classification and binary change detection (BCD). In this structure, the change region proposals are derived from the transformation (e.g., concatenation, differencing) of multi-temporal images, but after being processed by a convolutional neural network, there can be an incomplete response in the spatio-temporal features. Because of the high similarity of the color, texture, and geometric information of the ground objects in temporal high-resolution remote sensing imagery, this reduces the distinguishability of features and makes it difficult to identify changed areas. Meanwhile, there is less interaction between the BCD and classification, resulting in semantic inconsistency in changed areas. In this paper, the temporal-agnostic change region proposal network (TCRPN) is proposed, which is based on exploring the saliency of the changed regions in single-temporal images to highlight the changed areas in the spatio-temporal features and improve the response to change. As the changed areas can be the salient regions in the single-temporal images, a single-image salient area extractor (SSAE) is proposed to extract the salient areas from the different temporal images, obtaining salient change region candidates. As the change-related salient regions are temporally agnostic, temporal saliency fusion is used to integrate the candidates extracted from the single-temporal images to obtain a more reliable salient area map, where the salient area map is used to enhance the spatio-temporal features. Meanwhile, a shortcut is proposed to further make the change representation more distinguishable and suppress incorrectly highlighted regions. Directly utilizing multi-temporal images for change region proposal can reduce the change information loss and increase the interaction between the classification and BCD tasks to obtain better spatio-temporal features. The TCRPN is simple and flexible, and can be plugged into any multi-task SCD network. We selected four advanced multi-task SCD methods as the baseline, and added the TCRPN in their encoder or decoder part to conduct comprehensive experiments on three large-scale SCD datasets. The experimental results confirmed the effectiveness of the proposed method.

Evaluation of Camera Recognition Performance under Blockage Using Virtual Test Drive Toolchain.

This study is the first to develop technology to evaluate the object recognition performance of camera sensors, which are increasingly important in autonomous vehicles owing to their relatively low price, and to verify the efficiency of camera recognition algorithms in obstruction situations. To this end, the concentration and color of the blockage and the type and color of the object were set as major factors, with their effects on camera recognition performance analyzed using a camera simulator based on a virtual test drive toolkit. The results show that the blockage concentration has the largest impact on object recognition, followed in order by the object type, blockage color, and object color. As for the blockage color, black exhibited better recognition performance than gray and yellow. In addition, changes in the blockage color affected the recognition of object types, resulting in different responses to each object. Through this study, we propose a blockage-based camera recognition performance evaluation method using simulation, and we establish an algorithm evaluation environment for various manufacturers through an interface with an actual camera. By suggesting the necessity and timing of future camera lens cleaning, we provide manufacturers with technical measures to improve the cleaning timing and camera safety.

COLOR AND SIZE SORTING SYSTEM WITH AN ESP32-BASED ROBOT ARM

Robotics has seen an explosive increase in usage in the past few decades owing to its abundance of benefits and automation capabilities. The use of robotics is especially prominent in industries where the demand for precise and automatic robots in order to increase production efficiency is high. One of the robots commonly used in these industries is the arm robot model, which is a machine designed specifically to mimic some of the human arm’s capabilities in order to execute certain tasks over and over again, either autonomously or not. This paper will discuss the design of a robotic arm with five degrees of freedom capable of picking up and placing objects with three different colors and sorting the objects based on their size, starting from the largest to the smallest. The inclusion of an additional degree of freedom allows the robot to adjust the rotation of its grip to properly grab rotated objects. With an ESP32-CAM acting as its eyes, the robot is aided by a Python program run remotely on a separate Laptop in order to analyze video stream uploaded by the camera to determine the coordinates, color, size, and rotation of objects placed within the Detection Zone. The implementation of inverse kinematics equations run on an ESP32 microcontroller allows the robot to reach arbitrary coordinates specified by the Python program. Testing revealed that the resulting robot is able to perform the tasks it was designed to, namely recognizing and sorting colored boxes of different colors and sizes, with an accuracy 100% in recognition tasks and an accuracy of 91.5% in sorting tasks.