Image Frames Research Articles

High frame-rate imaging of the shape oscillations and spreading dynamics of picolitre droplets impacting on a surface

The post-impact dynamics and spreading rates of picolitre liquid droplets on surfaces are critical to many practical and industrial applications, as well as respiratory disease transmission mechanisms. Here we use a high framerate imaging method to explore the shape oscillations and spreading of individual ∼10–180 pl volume droplets (corresponding to ∼30–70 μm in initial droplet diameter) impacting on a surface under ambient conditions with 10 μs temporal resolution. The method allows the surface tension to be accurately extracted from the measured frequency of post-impact shape oscillations for sessile droplets in this size range with surface tensions greater than 40 mN m−1 and viscosities up to at least 3.2 mPa s. The Tanner's law model for predicting sessile droplet spreading rates provides an accurate account of the “steady-state” spreading rate for all droplets with surface tensions in the range 22–73 mN m−1 studied here. However, Tanner's law does not account for the delay in the onset of spreading observed for droplets in this size range, caused by competition between shape oscillations and spreading governing the morphology at short time periods, particularly for surface tensions >22 mN m−1.

Dynamic Hand Gesture Recognition for Indian Sign Language using Integrated CNN-LSTM Architecture

Human Centered Computing is an emerging research field that aims to understand human behavior. Dynamic hand gesture recognition is one of the most recent, challenging and appealing application in this field. We have proposed one vision based system to recognize dynamic hand gestures for Indian Sign Language (ISL) in this paper. The system is built by using a unified architecture formed by combining Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). In order to hit the shortage of a huge labeled hand gesture dataset, we have created two different CNN by retraining a well known image classification networks GoogLeNet and VGG16 using transfer learning. Frames of gesture videos are transformed into features vectors using these CNNs. As these videos are prearranged series of image frames, LSTM model have been used to join with the fully-connected layer of CNN. We have evaluated the system on three different datasets consisting of color videos with 11, 64 and 8 classes. During experiments it is found that the proposed CNN-LSTM architecture using GoogLeNet is fast and efficient having capability to achieve very high recognition rates of 93.18%, 97.50%, and 96.65% on the three datasets respectively.

Optical intraday variability of the blazar S5 0716+714

ABSTRACT We present an extensive recent multiband optical photometric observations of the blazar S5 0716+714 carried out over 53 nights with two telescopes in India, two in Bulgaria, one in Serbia, and one in Egypt during 2019 November – 2022 December. We collected 1401, 689, 14726, and 165 photometric image frames in B, V, R, and I bands, respectively. We monitored the blazar quasi-simultaneously during three nights in B, V, R, and I bands; four nights in B, V, and R; two nights in V, R, and I; five nights in B and R; and two nights in V and R bands. We also took 37 nights of data only in R band. Single band data are used to study intraday flux variability and two or more bands quasi-simultaneous observations allow us to search for colour variation in the source. We employ the power-enhanced F-test and the nested ANOVA test to search for genuine flux and colour variations in the light curves of the blazar on intraday time-scales. Out of 12, 11, 53, and 5 nights observations, intraday variations with amplitudes between ∼3 and ∼20 per cent are detected in 9, 8, 31 and 3 nights in B, V, R, and I bands, respectively, corresponding to duty cycles of 75, 73, 58, and 60 per cent. These duty cycles are lower than those typically measured at earlier times. On these time-scales colour variations with both bluer-when-brighter and redder-when-brighter are seen, though nights with no measurable colour variation are also present. We briefly discuss possible explanations for this observed intraday variability.

Pemberitaan penganiayaan David Ozora pada media Kompas.com: analisis wacana berbasis korpus

Cases of violence against children have recently become more frequent. Therefore, many parties have also evaluated their performance in handling these cases. One of them is the police, who are never out of the public spotlight. This study aims to analyze the discourse and dissect the frame of the police image regarding the David Ozora persecution case through Kompas.com media. This research uses a descriptive qualitative method and a corpus discourse analysis approach. The research data was taken from news articles published in Kompas.com media. The results showed that the relevant keyword used in Kompas.com media to report the persecution case of David Ozora was "persecution." In addition, Kompas.com's media strategy is framing the image of the Police by mentioning positions and titles. The media also tends to use positive words to disseminate the image of the Police regarding the achievements and accomplishments in handling the persecution case. This research is linguistic research that can be useful for adding knowledge references, especially in the field of corpus linguistics.

Anomalous behavior recognition of underwater creatures using lite 3D full-convolution network

Global warming and pollution could lead to the destruction of marine habitats and loss of species. The anomalous behavior of underwater creatures can be used as a biometer for assessing the health status of our ocean. Advances in behavior recognition have been driven by the active application of deep learning methods, yet many of them render superior accuracy at the cost of high computational complexity and slow inference. This paper presents a real-time anomalous behavior recognition approach that incorporates a lightweight deep learning model (Lite3D), object detection, and multitarget tracking. Lite3D is characterized in threefold: (1) image frames contain only regions of interest (ROI) generated by an object detector; (2) no fully connected layers are needed, the prediction head itself is a flatten layer of 1 × {mathcal{l}} @ 1× 1, {mathcal{l}}= number of categories; (3) all the convolution kernels are 3D, except the first layer degenerated to 2D. Through the tracking, a sequence of ROI-only frames is subjected to 3D convolutions for stacked feature extraction. Compared to other 3D models, Lite3D is 50 times smaller in size and 57 times lighter in terms of trainable parameters and can achieve 99% of F1-score. Lite3D is ideal for mounting on ROV or AUV to perform real-time edge computing.

Infrared Moving Small Target Detection Based on Space–Time Combination in Complex Scenes

In the infrared small target images with complex backgrounds, there exist various interferences that share similar characteristics with the target (such as building edges). The accurate detection of small targets is crucial in applications involving infrared search and tracking. However, traditional detection methods based on small target feature detection in a single frame image may result in higher error rates due to insufficient features. Therefore, in this paper, we propose an infrared moving object detection method that integrates spatio-temporal information. To address the limitations of single-frame detection, we introduce a temporal sequence of images to suppress false alarms caused by single-frame detection through analyzing motion features within the sequence. Firstly, based on spatial feature detection, we propose a multi-scale layered contrast feature (MLCF) filtering for preliminary target extraction. Secondly, we utilize the spatio-temporal context (STC) as a feature to track the image sequence point by point, obtaining global motion features. Statistical characteristics are calculated to obtain motion vector data that correspond to abnormal motion, enabling the accurate localization of moving targets. Finally, by combining spatial and temporal features, we determine the precise positions of the targets. The effectiveness of our method is evaluated using a real infrared dataset. Through analysis of the experimental results, our approach demonstrates stronger background suppression capabilities and lower false alarm rates compared to other existing methods. Moreover, our detection rate is similar or even superior to these algorithms, providing further evidence of the efficacy of our algorithm.

Efficient denoising of cold atom images using the optimized eigenface recognition algorithm.

Absorption imaging is a widely employed technique for detecting cold atom clouds and Bose-Einstein condensates (BECs). There are situations where such images may suffer from unwanted interference fringes, resulting in uncertainties in determining crucial parameters such as the atom number, temperatures, or even dynamics in small timescales. Reducing the acoustic vibrations and recording image frames synchronized with the source of such vibrations can largely reduce these fringes; however, some residual fringes still need to be taken care of for precision measurements. In this study, we propose an efficient image post-processing technique for noise reduction that effectively mitigates such interference patterns. Our approach makes use of the well-known eigenface recognition algorithm, combined with an optimized masking strategy applied to the image of the atomic cloud using a small number of basis sets. The use of a limited basis set ensures minimal computational time, allowing this method to be readily incorporated into every experimental run. Through the application of our technique, we successfully reduce interference fringes and improve the accuracy of parameter estimation by 50% in the absorption imaging of cold atoms. The temperature uncertainties of cold 87 R b atoms are reduced by more than 50% after the algorithm is applied. This approach holds significant promise for enhancing the reliability and precision of experimental measurements in diverse research fields where absorption imaging is employed.

Metaphor as a key tool in personal development discourse

Abstract In recent years, personal development has driven increasing interest, and the study of metaphor has expanded to various discourse types. This study aims to explore the metaphors in personal development discourse and determine their schematicity hierarchies, using Carol Dweck’s (2016) book Mindset: The New Psychology of Success as a case study. Metaphor Identification Procedure VU (Steen et al., 2010) is used to identify metaphors in the book and Zoltan Kövecses’s (2020) Extended Conceptual Metaphor Theory is used to establish the relationship between the metaphors identified and primary metaphors. The findings show that topics such as mindset, growth mindset, fixed mindset, success, and failure instantiate correlation and resemblance metaphors. In addition, all the correlation-based metaphors identified in the corpus possess full schematic hierarchies. It entails that they all consist of image schema, domain, frame and mental space levels. Moreover, the findings reveal that in different metaphorical expressions, the same image schema-level metaphor is likely to activate different domain, frame and mental space-level metaphors. Finally, some image schema-level metaphors share the same domain-level metaphor in different schematicity hierarchies, whereas others activate different domain-level metaphors in different schematicity hierarchies.

Deep learning in digital health with chatgpt: a study on efficient code generation

Abstract Background/Introduction Artificial Intelligence (AI) plays a significant role in the healthcare industry by providing innovative solutions to many health-related problems. Deep learning (DL) is a critical component in the development of AI-powered solutions; however, extensive knowledge is required to implement DL processes such as data preparation, model design, model training, and model evaluation. This has limited the widespread adoption of AI in the medical field, particularly in scenarios where non-technical professionals possess limited coding proficiency. Purpose This study evaluates the feasibility of using ChatGPT, a large language model developed by OpenAI, as an assistive tool for non-technical professionals to develop DL applications. The objective is to reduce the time and effort required in source code creation, while simplifying the overall process of application development. Methods ChatGPT was utilised to generate relevant source code for the creation of a DL application for echocardiogram view classification. Natural language input prompts were fed through the ChatGPT interface to produce modular scripts that fulfilled the purposes of video frame extraction, image pre-processing, dataset splitting, model training, and model evaluation. Input prompts were specified as a series of logical steps which explained the desired functionality, along with the necessary software libraries to be integrated. Results Experiments on code generation involved iteratively modifying input prompts through the rewording of sentences, reordering of steps, and usage of different libraries, to obtain working source code from ChatGPT responses. Results demonstrated that ChatGPT can generate fully usable programming scripts from natural language inputs, without the need for any modifications, to accomplish the various tasks involved in the DL process flow. Experiments were also conducted on locally sourced dobutamine stress echocardiogram videos, to verify script functionality and output reliability. The scripts successfully extracted, pre-processed, and split the video frames into training, validation, and testing sets. These datasets were then employed in the training and evaluation of a convolutional neural network which achieved an accuracy of above 80% when classifying seven different echocardiogram views. Conclusion ChatGPT has the potential to significantly reduce the time and effort required in developing DL applications. The successful implementation of the programming scripts suggest that ChatGPT can function as an assisting tool for non-technical professionals. Its ability to generate operational source code and streamline the development process could facilitate greater adoption of AI in healthcare and other industries. Future works shall explore the usage of ChatGPT in generating solutions to more heart-related use cases.Code generation and DL process flow

Real Time Detection Algorithm for Escape Ladders based on YOLOv5s

In the detection of escape ladders in the context of smart construction sites, due to the relatively small target size of the escape ladder compared to the entire input image frame, significant environmental interference, and high missed detection and false detection rates, an improved YOLOv5s escape ladder real-time detection algorithm is proposed by combining the attention mechanism network. The model uses CSPLocknet53 as the backbone network for feature extraction, introduces the attention module CA, and integrates spatial and channel information, while increasing a small amount of computation, performance has been significantly improved. Optimize the network structure of YOLOv5s algorithm, strengthen shallow feature weights to enhance small target detection effectiveness, add attention mechanisms to increase the weight of small targets and their surrounding features, and use Mosaic methods for data augmentation to improve detection accuracy and recall. After multiple repeated experiments, these experimental results have proven that the optimized YOLOv5s algorithm for real-time detection of escape ladders has an average detection accuracy (accuracy, recall) of (81.8, 82.6). Compared with the traditional YOLOv5s algorithm, the accuracy and recall have been improved by 1.4% and 1.2%, respectively. The optimized YOLOv5s algorithm can effectively improve the detection accuracy of real-time detection of escape ladders, and improve the detection and resolution performance of small escape ladder targets.

Visual–inertial object tracking: Incorporating camera pose into motion models

Visual object tracking for autonomy of aerial robots could become challenging especially in the presence of target or camera fast motions and long-term occlusions. This paper presents a visual-inertial tracking paradigm by incorporating the camera kinematics states into the visual object tracking pipelines. We gathered a dataset of image sequences with the addition of camera’s position and orientation measurements as well as the object’s position measurement. For the cases of long-term object occlusion, we provide ground-truth boxes derived from mapping the measured object position onto the image frame. A search zone proposal method is developed based on the estimation of object future position represented in the inertial frame and projected back onto the image frame using the camera states. This search zone, which is robust to fast camera/target motions, is fused into the original search zone settings of the base tracker. Also proposed is a measure indicating the confidence of a tracking structure in keeping track of a correct target and reporting the tracking failure in-time. Accordingly, the model updating mechanism of base tracker is modulated to avoid recovering of wrong objects as the target. The proposed modifications are benchmarked on nine visual object tracking algorithms including five state-of-art deep learning structures , namely DiMP, PrDiMP, KYS, ToMP, and MixFormer. Most of the trackers are remarkably improved by the modifications with up to 8% increase in precision. Modified PrDiMP tracker yields the best precision of 68.4%, more than all considered original (and modified) trackers. Source code and dataset are made available online.1

Framing Anxiety. Intermedial Techniques of the Uncanny

Abstract The article deals with techniques of the uncanny that are used in horror films, especially in movies that show frames within the image frame and particularly frames of television sets. The author situates the concrete device of framing in the context of medial technology and intermediality, not least the mediality of the television, its representation in movies and the resultant uncanny aspects. Distinctions are then made between the uncanny and anxiety with regard to the effects of framing, especially in relation to the specific status of a framed gaze. The author uses examples from Japanese and US-American horror films.1

Compilation of Integral Hermeneutics in the Image Frame Based on Heartless by Mehdi Akhavan Sales

Compilation of Integral Hermeneutics in the Image Frame Based on Heartless by Mehdi Akhavan Sales

Instant processing of large-scale image data with FACT, a real-time cell segmentation and tracking algorithm

Quantifying cellular characteristics from a large heterogeneous population is essential to identify rare, disease-driving cells. A recent development in the combination of high-throughput screening microscopy with single-cell profiling provides an unprecedented opportunity to decipher disease-driving phenotypes. Accurately and instantly processing large amounts of image data, however, remains a technical challenge when an analysis output is required minutes after data acquisition. Here, we present fast and accurate real-time cell tracking (FACT). FACT can segment ∼20,000 cells in an average of 2.5s (1.9-93.5 times faster than the state of the art). It can export quantifiable features minutes after data acquisition (independent of the number of acquired image frames) with an average of 90%-96% precision. We apply FACT to identify directionally migrating glioblastoma cells with 96% precision and irregular cell lineages from a 24h movie with an average F1 score of 0.91.

A real-time visual compass from two planes for indoor unmanned aerial vehicles (UAVs)

Improving the accuracy of pose determination of UAVs in a Global Positioning System-denied (GPS-denied) indoor environment, visual Simultaneous Localization And Mapping (vSLAM) techniques have attracted more attention from scholars. RGB-D (Red Green Blue-Depth) camera is a widely used visual sensor as it can recognize unknown environments and behave accordingly, which is valuable for UAVs. However, high computational resources are often required in featureless and uncharacteristic indoor environments to achieve the robust performance of pose decisiveness. To solve this challenge, this paper presents a novel real-time visual compass to estimate the three Degree-of-Freedom (DoF) relative orientations of an RGB-D camera, where the surface-normals-based RANdom Sample Consensus Model (RANSAC) is integrated. In addition, the Manhattan World (MW) assumption is exploited to simplify perception tasks by giving a way of probabilistically modeling background clutter. The effectiveness of the proposed estimator is comprehensively evaluated based on depth datasets from different indoor man-made scenes. And a universal parameter setting of the model is determined. The experiments demonstrated the effectiveness of the visual compass with an average absolute rotation error under 2°. Additionally, the average time needed by the algorithm to process an image frame is under 20 ms, satisfying real-time requirements. The robust achievement by both accuracy and timing indicates that our outperformed state-of-the-art approaches can be more conducive to indoor UAV design.

RELASI MEDIA MASSA JELANG PEMILU 2024 ANTARA PEMERINTAH DAN MASYARAKAT

Talking about the relationship between the media and the political sphere is a dilemmatic relationship. This is due to the attitude of media reporting which is not completely neutral from political intervention or capital patronage. Of course, this is something paradoxical considering that the media is the fourth pillar of democracy after the trias politica. The media should act as a watchdog in power so that checks and balances are created in the country and society. The media's observation is related to its central function as social correlations which lead the public to translate the various realities of life-span and national into the consumption of good print and electronic information. So, the media here has power over public knowledge through text and image framing so that it becomes the main public reference in shaping their views on the way government works. Information is the key word that links media relations with politics through the formation of public opinion on the news. This study aims to explain and analyze the tendency of mass media coverage in the context of the 2024 Presidential Election. The research method used is Robert N. Entman's framing analysis. The Research has shown that with mass media relations in politics by looking at media neutrality mass can at least be detected through; Mass media in determining news sources; Media using column and page limitations, mass media will observe the urgency of someone or a candidate couple in the election; There's room and place settings that are fairly wide against the activities of someone or a candidate couple, like the announcement on the first page of a newspaper.

Rancang Bangun Deteksi Objek dengan Metode Filter Warna HSV pada Sistem Klasifikasi Kualitas Biji Kopi Berbasis NVIDIA Jetson Nano

The Post-harvest coffee bean selection plays a crucial role in ensuring optimal bean quality during production processes. Currently, this process is manually conducted in Indonesia. Implementing computer vision can enhance the objectivity of the sorting process through machine vision. An effective object detection system is essential to support a prototype coffee bean quality classification system based on NVIDIA Jetson Nano. The Hue Saturation Value (HSV) color filter method proves effective in detecting objects within a given image frame. Performance evaluation is conducted by assessing the alignment between workflow design and system operation. While the webcam-based object detection system successfully deployed, its effectively identifies coffee bean objects, it faces limitations in detecting smaller, dark-colored beans beyond the specified HSV color threshold. These limitations are attributed to the webcam's specifications, including its rolling shutter, which results in a 'jello effect' when dealing with moving objects.

PMIndoor: Pose Rectified Network and Multiple Loss Functions for Self-Supervised Monocular Indoor Depth Estimation.

Self-supervised monocular depth estimation, which has attained remarkable progress for outdoor scenes in recent years, often faces greater challenges for indoor scenes. These challenges comprise: (i) non-textured regions: indoor scenes often contain large areas of non-textured regions, such as ceilings, walls, floors, etc., which render the widely adopted photometric loss as ambiguous for self-supervised learning; (ii) camera pose: the sensor is mounted on a moving vehicle in outdoor scenes, whereas it is handheld and moves freely in indoor scenes, which results in complex motions that pose challenges for indoor depth estimation. In this paper, we propose a novel self-supervised indoor depth estimation framework-PMIndoor that addresses these two challenges. We use multiple loss functions to constrain the depth estimation for non-textured regions. We introduce a pose rectified network that only estimates the rotation transformation between two adjacent frames of images for the camera pose problem, and improves the pose estimation results with the pose rectified network loss. We also incorporate a multi-head self-attention module in the depth estimation network to enhance the model's accuracy. Extensive experiments are conducted on the benchmark indoor dataset NYU Depth V2, demonstrating that our method achieves excellent performance and is better than previous state-of-the-art methods.

A Meteor Detection Algorithm for GWAC System

Compared with the international meteor surveillance systems, the ground wide angle camera (GWAC) system exhibits characteristics such as images with the resolution of 4K × 4K and single-site observation. These characteristics present challenges for meteor detection in the GWAC system. Consequently, this paper proposes a new meteor detection algorithm for the GWAC system on the base of the solely mini-GWAC system data algorithm. The new algorithm consists of the following key steps: (1) to compare differences between adjacent frames, applying block-based image binarization thresholds, and incorporating median filtering to reduce noise; (2) to adopt the probabilistic Hough transform (PHT) to identify moving objects and cluster them based on the origin moment of the line segments, while assessing the credibility of clustering; (3) to introduce the so-called maximum disappearance frame for moving objects in the tracking algorithm, enhancing the ability to track multi-frame moving objects. The utilization of the line segment inclination angle of the moving object as the direction of movement facilitates the tracking of multiple moving objects, thereby reducing the probability of mistakenly selecting single-frame moving objects; (4) to leverage the light curves of single-frame moving objects to select meteors to enhance the accuracy of meteor detection. Comparative experiments demonstrate that our proposed algorithm processes each frame image in just 0.39 s, achieving an accuracy of 89.8% in the dataset of 5856 adjacent frames. The experimental results indicate that the algorithm achieved an accuracy of 90.27% when applied in the meteor detection of the image data captured by the GWAC system from Dec. 10th to 19th in 2019 and 2021, obtaining excellent detection results.

Adaptive undersampling and short clip-based two-stream CNN-LSTM model for surgical phase recognition on cholecystectomy videos

Surgical phase recognition is challenging due to overfitting problems caused by imbalanced data among surgical phases. We proposed an adaptive sampling rate-based undersampling method that could generate the number of each surgical phase data similarly to alleviate biased learning. To improve the performance of our method, we also introduced a two-stream CNN-LSTM model that could extract temporal information on behavioral changes between each image frame. First, we extracted a total of 40,236 short clips using an adaptive subsampling rate from the entire video. Each short clip was entered into a pre-trained GoogLeNet. The output with visual information was then immediately fed into a sequence-to-sequence LSTM model to extract temporal information of neighbor frames within a short clip. At the same time, another sequence-to-vector LSTM was used, to extract temporal information from all successive image frames to predict the final surgical phase. The proposed method was evaluated with a public dataset Cholec80. The proposed approach outperformed state-of-the-art methods, showing a high F1-score of 87.12% and an AUC of 98.00%. In addition, the F1-score deviation between all phases decreased by about 10% compared to that before applying undersampling. Experimental results confirmed that employing our proposed method could learn enrich temporal information from short clips. It outperformed the conventional one-stream CNN-LSTM architecture.