Appearance Variations Research Articles

Evaluation of YOLO Efficiency in Automatic Orange Detection in Multi-Exposure Images

Abstract. Brazil is the largest producer of oranges in the world and the automatic detection of fruits has been a challenging task in the context of remote sensing, due to variations in fruit appearance, changes in lighting and occlusions of foliage and neighboring fruits. In this sense, this paper focus on the detection of oranges in multispectral images, with different spectral bands and exposures, using a convolutional neural network (CNN) known as YOU ONLY LOOK ONCE (YOLO). The results indicate that, after 300 epochs, the model demonstrated an accuracy of 81.5% and an approximate recovery rate of 85%. Shutter speeds 1/640s and 1/250s are not suitable for detection due to low light and overexposure, respectively. Intermediate values may be more suitable for identifying a larger number of fruits.

Finding MeVO: Identifying Intracranial Medium-Vessel Occlusions at CT Angiography.

The development of methods to detect and treat intracranial large-vessel occlusions (LVOs) has revolutionized the management of acute ischemic stroke. CT angiography (CTA) of the head and neck is effective in depicting LVOs and widely used in the evaluation of patients who have had a stroke. Ongoing efforts are now focused on the potential to detect and treat intracranial medium-vessel occlusions (MeVOs), which by definition are smaller than LVOs and thus more difficult to detect with CTA. The authors review common and variant anatomies of medium-sized cerebral arteries and the appearance of a variety of MeVOs on CT angiograms. Possible pitfalls in MeVO detection include rare anatomic variants, calcified thrombi, and stump occlusions. Current recommendations for performing CTA and ancillary methods that might aid in MeVO detection are discussed. Understanding the relevant anatomy and the variety of appearances of MeVOs aids radiologists in identifying these occlusions, particularly in the setting of urgent stroke. ©RSNA, 2024 See the invited commentary by Ospel and Nguyen in this issue.

Automated classification in turtles genus Malayemys using ensemble multiview image based on improved YOLOv8 with CNN

In Thailand, two snail-eating turtle species in the genus Malayemes (M. subtrijuga and M. macrocephala) are protected animals in which smuggling and trading are illegal. Recently, a new species M. khoratensis has been reported and it has not yet been considered as protected animal species. To enforce the law, species identification of Malayemes is crucial. However, it is quite challenging and requires expertise. Therefore, a simple tool, such as image analysis, to differentiate these three snail-eating species would be highly useful. This study proposes a novel ensemble multiview image processing approach for the automated classification of three turtle species in the genus Malayemys. The original YOLOv8 architecture was improved by utilizing a convolutional neural network (CNN) to overcome the limitations of traditional identification methods. This model captures unique morphological features by analyzing Malayemys species images from various angles, addressing challenges such as occlusion and appearance variations. The ensemble multiview strategy significantly increases the YOLOv8 classification accuracy using a comprehensive dataset, achieving an average mean average precision (mAP) of 98% for the genus Malayemys compared with the nonensemble multiview and single-view strategies. The species identification accuracy of the proposed models was validated by comparing genetic methods using mitochondrial DNA with morphological characteristics. Even though the morphological characteristics of these three species are ambiguous, the mitochondrial DNA sequences are quite distinct. Therefore, this alternative tool should be used to increase confidence in field identification. In summary, the contribution of this study not only marks a significant advancement in computational biology but also supports wildlife and turtle conservation efforts by enabling rapid, accurate species identification.

4Seasons: Benchmarking Visual SLAM and Long-Term Localization for Autonomous Driving in Challenging Conditions

AbstractIn this paper, we present a novel visual SLAM and long-term localization benchmark for autonomous driving in challenging conditions based on the large-scale 4Seasons dataset. The proposed benchmark provides drastic appearance variations caused by seasonal changes and diverse weather and illumination conditions. While significant progress has been made in advancing visual SLAM on small-scale datasets with similar conditions, there is still a lack of unified benchmarks representative of real-world scenarios for autonomous driving. We introduce a new unified benchmark for jointly evaluating visual odometry, global place recognition, and map-based visual localization performance which is crucial to successfully enable autonomous driving in any condition. The data has been collected for more than one year, resulting in more than 300 km of recordings in nine different environments ranging from a multi-level parking garage to urban (including tunnels) to countryside and highway. We provide globally consistent reference poses with up to centimeter-level accuracy obtained from the fusion of direct stereo-inertial odometry with RTK GNSS. We evaluate the performance of several state-of-the-art visual odometry and visual localization baseline approaches on the benchmark and analyze their properties. The experimental results provide new insights into current approaches and show promising potential for future research. Our benchmark and evaluation protocols will be available at https://go.vision.in.tum.de/4seasons.

Using 3D Hand Pose Data in Recognizing Human–Object Interaction and User Identification for Extended Reality Systems

Object detection and action/gesture recognition have become imperative in security and surveillance fields, finding extensive applications in everyday life. Advancement in such technologies will help in furthering cybersecurity and extended reality systems through the accurate identification of users and their interactions, which plays a pivotal role in the security management of an entity and providing an immersive experience. Essentially, it enables the identification of human–object interaction to track actions and behaviors along with user identification. Yet, it is performed by traditional camera-based methods with high difficulties and challenges since occlusion, different camera viewpoints, and background noise lead to significant appearance variation. Deep learning techniques also demand large and labeled datasets and a large amount of computational power. In this paper, a novel approach to the recognition of human–object interactions and the identification of interacting users is proposed, based on three-dimensional hand pose data from an egocentric camera view. A multistage approach that integrates object detection with interaction recognition and user identification using the data from hand joints and vertices is proposed. Our approach uses a statistical attribute-based model for feature extraction and representation. The proposed technique is tested on the HOI4D dataset using the XGBoost classifier, achieving an average F1-score of 81% for human–object interaction and an average F1-score of 80% for user identification, hence proving to be effective. This technique is mostly targeted for extended reality systems, as proper interaction recognition and users identification are the keys to keeping systems secure and personalized. Its relevance extends into cybersecurity, augmented reality, virtual reality, and human–robot interactions, offering a potent solution for security enhancement along with enhancing interactivity in such systems.

Hypoechoic ultrasonographic findings in the patellar ligaments are common in riding and trotting horses in training (116 cases).

Patellar ligament (PL) injuries are increasingly being reported in horses, but few studies have described the normal PL ultrasonographic appearance in horses. The aims of this prospective observational study were to describe the ultrasonographic appearance of the PLs and infrapatellar fat pad in a population of horses in training and to relate the ultrasonographic findings to objectively measured movement asymmetry. B-mode and color Doppler ultrasonographic examination of the PLs and infrapatellar fat pad in both hind limbs and objective gait analyses were performed on the 116 riding and trotting horses included in the study. The association between ultrasonographic findings, horse age, and movement asymmetry during the trot was then investigated. Distinct or diffuse hypoechoic regions were commonly found in the intermediate PL (24/116; 20.7%), especially in the caudal aspect of the mid-third of the ligament. The infrapatellar fat pad had a hypoechoic striated appearance in all horses except one, in which it was hyperechoic. No association was found between ultrasonographic findings in the PLs and infrapatellar fat pad and lameness. It is important to recognize that there is biological variation in PL appearance, which may or may not be associated with pain in this area, therefore emphasizing the use of local analgesia to determine the location of the lameness.

Organoleptic profiling for demand led breeding of eggplant (Solanum melongena L.) suitable for Kerala market

In order to develop eggplant hybrids with consumer acceptance, an organoleptic evaluation of fruits in two different sets of eggplant genotypes was conducted by a panel of 15 judges with 21 descriptors, following a quantitative descriptive analysis (QDA). In 2023, twenty genotypes were evaluated as the first set to identify suitable parents for hybridization. The results showed significant variation in odour, appearance, texture, flavor and taste, and overall quality attributes. From the first set, five genotypes (Ponni, Vengeri, IC618016, IC636521, and IC624240) were selected to produce ten F1 hybrids, and they were further evaluated, along with parents and three popular varieties as check in 2024. In the second set, many descriptors showed no significant variation. F1 hybrid, Vengeri x IC636521, showed higher yield and overall quality attributes, and most of the other hybrids (seven) were high yielders over popular checks with on par for overall quality. The findings suggest the role of organoleptic evaluation in selection and development of quality breeding materials. Keywords: Odour, Appearance, Texture, Flavour, Taste, Overall quality

A Hybrid Approach for Robust Object Detection: Integrating Template Matching and Faster R-CNN

Object detection is a critical task in computer vision, with applications ranging from autonomous vehicles to medical imaging. Traditional methods like template matching offer precise localization but struggle with variations in object appearance, while deep learning approaches such as Faster R-CNN excel in handling diverse and complex datasets but often require extensive computational resources and large amounts of labeled data. This paper proposes a hybrid approach that integrates template matching with Faster R-CNN to leverage the strengths of both techniques. By combining the accuracy of template matching with the robustness and generalization capabilities of Faster R-CNN, our method achieves superior performance in challenging scenarios, including objects with occlusions, varying scales, and complex backgrounds. Extensive experiments demonstrate that the hybrid model not only enhances detection accuracy but also reduces computational load, making it a practical solution for real-world applications.

Dwarf galaxies in the MATLAS Survey: Hubble Space Telescope observations of the globular cluster systems of 74 ultra-diffuse galaxies

Ultra-diffuse galaxies (UDGs), characterised by their low surface brightness and large physical size, constitute a subclass of dwarf galaxies that challenge our current understanding of galaxy formation and evolution. In this paper, we probe the properties of 74 UDGs, identified in the MATLAS survey, based on a comprehensive study of their globular cluster (GC) populations. We obtained high-resolution HST imaging of these galaxies using the ACS F606W and F814W filters, which allowed us to select GCs on the basis of the colour and concentration index. After a background subtraction and completeness correction, we calculated an overall total of 387 GCs. The number of GCs per galaxy ranges from 0 to 38, with the majority (64%) having low counts (0 − 2 GCs). On average, the more massive UDGs tend to host a larger number of GCs. We find that our UDGs have specific frequencies (SN) ranging from 0 to 91, with a small population (9%) having SN > 30. The median SN of our sample is similar to the one for the Perseus cluster UDGs, despite the fact that our UDGs are found in lower density environments. The SN measurements for individual galaxies can extend beyond those found in Perseus, but remain below the values found for UDGs in the Virgo and Coma cluster. Based on a trending analysis of the SN values with the host galaxy properties, we find trends with host galaxy size, roundness, colour, and local density. For the UDGs with sufficiently high statistics, we studied 2D density maps of the GC distributions, which display a variety of appearances: symmetric, asymmetric, off-centre, and elongated. The UDGs with disturbed density maps also show disturbed stellar light morphologies. We further quantified the distribution by modelling it with a Sérsic profile, finding Re, GC/Re, gal ∼ 1.0, which indicates that the GCs follow the stellar light of the host galaxy.

An adaptive learning based aberrance repressed multi-feature integrated correlation filter for Visual Object Tracking (VOT)

Target tracking via Correlation Filter (CF) is a hot research area of computer vision domain, and offers various credible benefits. Existing CF algorithms face challenges when there are target appearance variations due to background noise, scale and illumination changes, occlusion, and fast motion, which severely degrades the overall tracker performance. To get maximum benefits, an object tracker should perform well with the less computational burden in the presence of real time challenging situations. To address this issue, a novel visual object trackeris proposed based on multi feature fusion and adaptive learning technique with aberrance suppression. At first, multiple features i.e., Histogram of gradient (HOG), Color Naming (CN), saliency, and gray level intensities are combined using feature fusion technique. Further, based on the evaluation of final fused response map using Peak-to-Sidelobe Ratio (PSR), an adaptive learning strategy is integrated to improve the learning phase of tracker. Tracking results show that the proposed strategy beats the other modern CF trackers with Distance Precision (DP) scores of 88.2%, 85.9%, and 74.1% and 64.7% over OTB2013, OTB2015, and TempleColor128 and UAV123 datasets respectively.

The Acceptance of Seitan Serunding as Meat Substitute: Food Experts Point of View

The global movement towards a plant-based diet, known as the Plant-Based Revolution, has garnered significant attention for its potential health benefits, environmental sustainability, and ethical considerations. Despite the increasing availability and awareness of plant-based options, sensory obstacles hinder their widespread acceptance among diverse consumer groups. A notable challenge lies in the inability of many meat substitute products to accurately replicate the authentic taste and texture of real meat, which influences consumer acceptance of the product. Therefore, from the perspective of food experts, this paper addresses a critical aspect of sensory acceptance in the context of Seitan Serunding, a plant-based meat substitute. The methodology is divided into two phases: Seitan Serunding development and sensory expert evaluation. Seitan Serunding Development used the recipe obtained from the Seitan Society group, where a community of enthusiasts shares their expertise and insights. For sensory expert evaluations, this study enlisted seven experienced culinary and gastronomy lecturers, food testers, and food technologists to deliver detailed, accurate, and insightful assessments of the Seitan Serunding products. These experts must inherently possess the ability to discern subtle variations in taste, texture, aroma, appearance, and overall acceptability by using a five-point Likert scale for each item evaluated. Then, this evaluation was analysed using descriptive analyses. Findings reveal that Seitan Serunding's delicious taste and close resemblance to traditional Meat Serunding, with a slight difference in aftertaste, could refine it for a more authentic experience through seasoning adjustments. This study contributes to the discourse on meat substitutes, highlighting the need for future research to explore diverse preparation methods for seitan and conduct comparative studies with a broader range of meat substitutes to address existing gaps in understanding and acceptance.

Enhancing Inland Waterway Safety and Management through Machine Learning-Based Ship Detection

Efficient ship detection is essential for inland waterway management. Recent advances in artificial intelligence have prompted research in this field. This study introduces a real-time ship detection model utilizing computer vision and the YOLO object detection framework. The model is designed to identify and locate common inland waterway vessels, such as container ships, passenger vessels, barges, ferries, canoes, fishing boats, and sailboats. Data augmentation techniques were employed to enhance the model's ability to handle variations in ship appearance, weather, and image quality. The system achieved a mean Average Precision (mAP) of 98.4%, with precision and recall rates of 96.6% and 95.0%, respectively. These results demonstrate the model's effectiveness in practical applications. Its ability to generalize across diverse vessel types and environmental conditions suggests its potential integration into video surveillance for improved maritime safety, traffic control, and search and rescue operations.

Beyond the visible: A survey on cross-spectral face recognition

Cross-spectral face recognition (CFR) refers to recognizing individuals using face images stemming from different spectral bands, such as infrared versus visible. While CFR is inherently more challenging than classical face recognition due to significant variation in facial appearance caused by the modality gap, it is useful in many scenarios including night-vision biometrics and detecting presentation attacks. Recent advances in deep neural networks (DNNs) have resulted in significant improvement in the performance of CFR systems. Given these developments, the contributions of this survey are three-fold. First, we provide an overview of CFR, by formalizing the CFR problem and presenting related applications. Secondly, we discuss the appropriate spectral bands for face recognition and discuss recent CFR methods, placing emphasis on deep neural networks. In particular we describe techniques that have been proposed to extract and compare heterogeneous features emerging from different spectral bands. We also discuss the datasets that have been used for evaluating CFR methods. Finally, we discuss the challenges and future lines of research on this topic.

Taxonomy, morphology and phylogenetic placement of a new species Nitella pluripapillifera sp. nov. (Charales, Charophyta) from Japan

ABSTRACT We examined the morphology and taxonomy of specimens of the genus Nitella, collected from the main island of Okinawa, Japan. Based on their vegetative and reproductive characteristics, the samples were most similar to Nitella tumulosa, as the two species have a large monoicous thallus without mucus, an abbreviated two-celled dactyl and papillate oospore walls. Nevertheless, the two species can be differentiated based on variations in the overall appearance of thalli and the size of oogonia. Moreover, scanning electron microscopy observations revealed the detailed structures of oospores of specimens collected from Okinawa, and their oospore characteristics were clearly distinguishable from those of N. tumulosa and other related taxa. Additionally, molecular phylogenetic analyses demonstrated that the specimens collected from the main island of Okinawa were phylogenetically separated from a clade comprising specimens of N. tumulosa. Therefore, we propose a new species from the specimen collected from the main island of Okinawa as, Nitella pluripapillifera sp. nov.

Contrastive representation enhancement and learning for handwritten mathematical expression recognition

Handwritten mathematical expression recognition (HMER) is an appealing task due to its wide applications and research challenges. Previous deep learning-based methods used string decoder to emphasize on expression symbol awareness and achieved considerable recognition performance. However, these methods still meet an obstacle in recognizing handwritten symbols with varying appearance, in which huge appearance variations significantly lead to the ambiguity of symbol representation. To this end, our intuition is to employ printed expressions with unified appearance to serve as the template of handwritten expressions, alleviating the effects brought by varying symbol appearance. In this paper, we propose a contrastive learning method, where handwritten symbols with identical semantic are clustered together through the guidance of printed symbols, leading model to enhance the robustness of symbol semantic representations. Specifically, we propose an anchor generation scheme to obtain printed expression images corresponding with handwritten expressions. We propose a contrastive learning objective, termed Semantic-NCE Loss, to pull together printed and handwritten symbols with identical semantic. Moreover, we employ a string decoder to parse the calibrated semantic representations, outputting satisfactory expression symbols. The experiment results on benchmark datasets CROHME 14/16/19 demonstrate that our method noticeably improves recognition accuracy of handwritten expressions and outperforms the standard string decoder methods.

A review on video person re-identification based on deep learning

Person Re-Identification (ReID) is an essential technology for matching a person across non-overlapping cameras. It has attracted increasing attention in recent years due to its wide range of applications in various real-world scenarios such as security surveillance and criminal investigation. Different from other person ReID tasks, video-based ReID uses a video clip as the retrieval input, which can provide more promising ReID performance because that the video has rich information on appearance, motion cues and pose variations on temporal pipeline. Over the last few years, many deep learning-based video person ReID have been proposed to address various challenges, such as illumination variation, complex background, occlusion, etc. To provide a more comprehensive and readable review on existing video-based person ReID methods, we propose a novel taxonomy method that observes existing methods from four perspectives: data, algorithms, computing power, and applications. Specifically, we first introduce some popular datasets and evaluation criterion used for video-based person ReID. Next, from limited data and little annotation view, we introduce data augmentation and unsupervised learning ReID. From algorithm view, we focus on reviewing supervised methods including spatial feature learning, temporal feature learning and spatio-temporal feature learning, and further discuss and conduct a systematic comparison among these approaches. From complex open-world application view, we mainly summarized domain adaption and multimodal ReID. From insufficient GPU computing power view, we mainly discuss modality-agnostic unified large-scale ReID and their lightweighting. Finally, we provide a discussion of open problems and potential research directions for the community.

Lightweight detection of small tools for safer construction

Construction sites present significant potential safety hazards to the workers, with hand tools being a major source of injuries. This paper presents a Lightweight approach for Small Tools Detection (LSTD) method using a deep neural network for real-time detection of small construction tools. LSTD utilizes a lightweight backbone with Dynamic Feature Extraction, Accurate Separated Head, and Integrated Feature Fusion, reducing parameters by 73% and computations by 28% versus YOLOv5 while achieving 87.3% mean Average Precision (mAP) on challenging construction site datasets. Additional modules enhance detection recall and robustness to appearance variation and scale changes. Extensive experiments demonstrate LSTD's superior performance in misty conditions and illumination changes. With high accuracy in a compact 2.87 M parameter network, LSTD brings ubiquitous worker safety monitoring via edge devices closer to reality. The proposed model marks a significant advancement in improving safety in high-risk construction environments.

Online discrimination-correction subnet for background suppression and dynamic template updating in Siamese visual tracking

The offline Siamese tracking methods have recently attracted much attention due to their impressive performance on speed and accuracy. However, they ignore the target and background information during tracking, thus lacking sufficient discrimination ability to handle complex background interference, and cannot robustly adapt to sharp appearance variations in challenging situations, such as scale variation, rotation, occlusion, and background clutter. To address the drawbacks above, we propose an online discrimination-correction subnet, which discriminates and corrects the tracking results obtained by the Siamese tracker through online learning, and further guides the template update. Firstly, a feature refinement module is designed to enhance the discriminative ability of features, which compresses and combines target features based on the importance of feature channels to obtain target-specific features. On this basis, an online discriminator module is proposed to learn the decision boundary between target and background through samples collected online to suppress background interference. In addition, a sample equilibrium strategy is proposed to alleviate the imbalance in the distribution of positive and negative samples during online training. Finally, to handle sharp target appearance variations, a robust template updating strategy is proposed to screen high-quality historical samples to generate dynamic templates. To evaluate the generalization ability and effectiveness of our method, we apply it to four classical Siamese trackers, namely SiamFC, SiamRPN++, SiamCAR, and TransT. Extensive experiments on seven challenging benchmarks demonstrate that our method significantly improves the baseline methods and achieves outstanding performance compared with state-of-the-art trackers.

Insight into the changes in active metabolite profiles of noni (Morinda citrifolia L.) fruit subjected to different drying treatments

Noni fruit is renowned for its abundance of bioactive compounds. Drying is an important method for processing functional products derived from noni. However, limited information exists on how drying methods affect the active metabolite profiles of noni fruit. This study investigated the impact of four common drying methods, including hot-air drying (HAD), vacuum freeze drying (VFD), microwave drying (MWD), and far infrared drying (FID), on the physicochemical indexes, bioactive components, and functional properties of dried noni fruit slices using targeted and untargeted metabonomics analysis. The results showed significant variations in appearance, water migration, and microstructure of dried noni fruit slices subjected to the four drying methods. VFD treatment yielded better dried noni fruit products when compared to other drying methods. The superiority of VFD treatment was due to its uniform stratification, reduced collapse, better retention of bioactive components and antioxidants, and higher enzyme inhibitory rates. These findings suggest that VFD method is ideal for obtaining premium bioactive profiles and maintaining the biological activity of noni fruit.

NeRF-Art: Text-Driven Neural Radiance Fields Stylization.

As a powerful representation of 3D scenes, the neural radiance field (NeRF) enables high-quality novel view synthesis from multi-view images. Stylizing NeRF, however, remains challenging, especially in simulating a text-guided style with both the appearance and the geometry altered simultaneously. In this paper, we present NeRF-Art, a text-guided NeRF stylization approach that manipulates the style of a pre-trained NeRF model with a simple text prompt. Unlike previous approaches that either lack sufficient geometry deformations and texture details or require meshes to guide the stylization, our method can shift a 3D scene to the target style characterized by desired geometry and appearance variations without any mesh guidance. This is achieved by introducing a novel global-local contrastive learning strategy, combined with the directional constraint to simultaneously control both the trajectory and the strength of the target style. Moreover, we adopt a weight regularization method to effectively suppress cloudy artifacts and geometry noises which arise easily when the density field is transformed during geometry stylization. Through extensive experiments on various styles, we demonstrate that our method is effective and robust regarding both single-view stylization quality and cross-view consistency.