Online pedestrian tracking via saliency-based H-S histogram

Object tracking in video is a challenging problem in several applications such as video surveillance, video compression, video retrieval, and video editing. Tracking an object in a video is not easy due to loss of information caused by illumination changing in a scene, occlusions with other objects, similar target appearances, and inaccurate tracker responses. In this paper, we present a novel object detection and tracking algorithm via structured output prediction classifier. Given an initial bounding box with its position, we first divide it into sub-blocks with a predefined size. Next, we extract the features from each sub-blocks with Haar-like features method. And then we learn those features with a structured output prediction classifier. We treat the sub-blocks obtained from the initial bounding box as positive samples and then randomly choose negative samples from search windows defined by the specific area around the bounding box. After that, we obtain prediction scores for each sub-blocks both from positive and negative samples. We construct a region-graph with sub-blocks as nodes and classifier’s score as weight to detect the target object in each frame. Our experimental results show that the proposed method outperforms state-of-the-art object tracking algorithms.KeywordsObject DetectionObject TrackingSupport Vector Machine

Software was developed in Python for the digital processing of object images before their detection using the You Only Look Once (YOLO) artificial neural network. Detection was carried out on object images, specifically vehicles and other road users. The preprocessing of images was performed through histogram equalization and local contrast enhancement. The original images were read from video cameras or graphic files. Image detection was performed using the medium-sized YOLO convolutional neural network model, YOLOv8m. As a result of detection, the studied objects, particularly cars, were highlighted with rectangular bounding boxes. To evaluate the accuracy of object detection, several metrics (parameters) were used: Precision, Recall, Intersection over Union (IoU), F1, and Average Precision (AP). The YOLO network was pre-trained on the Common Objects in Context dataset. The YOLO neural network returns the object recognition confidence, the coordinates of its center (x, y) on the image, and its width and height (w, h). The detected objects are marked with rectangular bounding boxes. The positioning of objects in the images was manually performed using the Roboflow tool, which allows for accurate spatial positioning of each object. The study of the impact of image preprocessing on the accuracy of object detection by the YOLO network was conducted using a typical traffic scene image. After histogram equalization, the histogram becomes more symmetrical and uniform, improving the visual quality of both dark and bright areas. This led to improved object detection accuracy across almost all metrics. The increase in detection accuracy by the IoU parameter is 0.169. The summary improvement in detection accuracy by the IoU, F1, AP parameters is 0.502. It was shown that after image preprocessing, detection accuracy increased, and all vehicles were correctly detected. The developed software can be used in various computer vision systems as well as in Internet of Things systems for remote monitoring and control.

Delayed or missed diagnosis of perilunate or lunate dislocations can lead to significant morbidity. Advances in computer vision provide an opportunity to improve diagnostic performance. In this study, a deep learning algorithm was used for detection of perilunate and lunate dislocations on lateral wrist radiographs. A total of 435 lateral wrist radiographs were labeled as normal or pathologic (perilunate or lunate dislocation). The lunate in each radiograph was segmented with a rectangular bounding box. Images were partitioned into training and test sets. Two neural networks, consisting of an object detector followed by an image classifier, were applied in series. First, the object detection module was used to localize the lunate. Next, the image classifier performed a binary classification for normal or pathologic. The accuracy, sensitivity, and specificity of the overall system were evaluated. A receiver operating characteristic curve and the associated area under the curve were used to demonstrate the overall performance of the computer vision algorithm. The lunate object detector was 97.0% accurate at identifying the lunate. Accuracy was 98.7% among the subgroup of normal wrist radiographs and 91.3% among the subgroup of wrist radiographs with perilunate/lunate dislocations. The perilunate/lunate dislocation classifier had a sensitivity (recall) of 93.8%, a specificity of 93.3%, and an accuracy of 93.4%. The area under the curve was 0.986. The authors have developed a proof-of-concept computer vision system for diagnosis of perilunate/lunate dislocations on lateral wrist radiographs. This novel deep learning algorithm has potential to improve clinical sensitivity to ultimately prevent delayed or missed diagnosis of these injuries.

Abstract. Ship detection plays an important role in military and civil fields. Despite it has been studied for decays, ship detection in remote sensing images is still a challenging topic. In this work, we come up with a novel ship detection framework based on the keypoint extraction technique. We use a convolutional neural network to detect ship keypoints and then cluster the keypoints into groups, where each group is composed of keypoints belonging to the same ship. The choice of the keypoints is specifically considered to derive an effective ship representation. One keypoint is located at the center of the ship and the rest four keypoints are located at the head, the tail, the midpoint of the left side and the midpoint of the right side, respectively. Since these keypoints are distributed in a diamond, we name our network DiamondNet. In addition, a corresponding clustering algorithm based on the geometric characteristics of the ships is proposed to cluster keypoints into groups. We demonstrate that our method provides a more flexible and effective way to represent ships than the popular anchor-based methods, since either the rectangular bounding box or the rotated bounding box of each ship instance can be easily derived from the ship keypoints. Experiments on two datasets reveal that our DiamondNet reaches the state-of-the-art results.

This paper presents efficient object tracking in video sequences using multiple features by embedding mean shift into particle filters. When clutter background and occlusions are present. Particle filtering is used because it is very robust and performs well for non-linear and non-Gaussian dynamic state estimation problems. The image features, such as shape, texture, color, contours, and random motion appearance can be used to track the moving object(s) in videos. We proposed a smart video surveillance system with real-time as well as offline stored video database for moving object detection, classification and tracking capabilities. The graphical user interface of the proposed system using MATLAB 2012b is implemented that operates on both color and gray scale video images from a stationary camera. In this method, we proposed real time moving object detection and tracking system using static webcam that can processes 800*600, 640*480, and 320*240 resolution video sequences for capturing live scene as well as stored database of segmented videos. Issues related with object detection and tracking is jointly employed using mean shift and particle filters. Tracker will estimate the dynamic shape and random appearance of objects. Tracking requires location and shape of object in every segmented frame. Rectangular bounding box is used to improve the estimate of its shape and appearance. Target object may experience partial occlusions, intersection with other objects with similar color distributions, abrupt motion speed changes, and cluttered background. Test result shows improvement in terms of robustness, tracking drifts, accuracy of tracked bounding box to occlusions.

In visual tracking, developing an efficient appearance model is a challenging task due to the influence of various factors, such as illumination variation, occlusion, background clutter, and so on. Existing tracking algorithms use appearance samples from previous frames to form a template set upon which target appearance models are built. However, these appearance models are data-dependent, so they may be corrupted by significant appearance variation. It is difficult to update the templates in challenging environments. In this paper, we propose a robust visual tracking algorithm with an adaptive appearance model using a point-to-set metric learning technique. To do this, we first model a target representation using a set of target templates and a regularized affine hull (RAH) spanned by the target templates. Then, we learn a point-to-set distance metric, which is incorporated into the optimization process to obtain an adaptive target representation. The RAH model covers unseen target appearances by affine combinations of the target templates. Based on the proposed target appearance model, we design an effective template update scheme by adjusting the weights of the target templates. Experimental results on challenging video sequences with comparisons to several state-of-the-art tracking algorithms demonstrate the effectiveness and robustness of the proposed tracking algorithm.

Target tracking is an important part of many applications in computer vision. With continuous researching and developing, more and more advanced tracking algorithms have been put forward. Therefore, a benchmark and dataset used to evaluate the most advanced tracking algorithms are needed. One of the most widely used benchmarks is Online Tracking Benchmark (OTB). This benchmark has a clear statement of the video attributes, and each frame in the sequences is appropriately provided with the ground-truth annotations. There may be some errors due to the annotations done by manual operation for bounding box and thus we find and modify the annotations that have some errors. The error means the bounding box for tracking target in some frames is beyond boundaries of corresponding frames. Then we study the effect of these small errors on the tracking algorithm evaluation in the corresponding video sequences.

Real-time object tracking via self-adaptive appearance modeling

Visual tracking is an open issue in computer vision. Designing an robust tracking algorithm is a challenging problem due to complicated appearance variations, such as partial occlusion, illumination variations, fast motion and out-of-plane rotation. Some tracking algorithms use a set of templates to represent a target candidate. Such representations are not robust to drastic appearance variations. In order to alleviate the influence of appearance variations and outliers, we propose a novel tracking algorithm based on a robust Bayesian matrix factorization, where sample data is decomposed into a basis matrix and a coefficient matrix. The sample data is consist of previous tracking results. A column vector is stacked by a tracking result in a frame. A target candidate is represented by a linear combinations of the columns in the basis matrix. The matrix factorization can capture the correlation between different features in sample data. Also the appearance variations in tracking processing can be learnt in matrix factorization. Experimental results demonstrate the appearance models is effective and the proposed tracker in a particle filter tracking framework is robust to outliers and complicated appearance variations.

Detecting three-dimensional (3D) objects has attracted the growing attention in 3D computer vision research. However, the low precision value is a significant trouble in many applications, like automatic driving, robotics, and medical applications. To solve the low precision problem, we use the 3D EIoU loss as localization loss, which emphasizes on the overlapping degree, central position, and structural shape between two rectangular bounding boxes. Furthermore, we propose an EIoU-NMS to enhance the process of suppressing redundant detecting boxes. By incorporating the 3D EIoU loss and EIoU-NMS into the PointPillars one-stage detectors, the detection performance for 3D point cloud objects is considerably improved. By using the KITTI benchmark, empirical experiments have been conducted to measure the average precision (AP) values for detecting Car, Cyclist, and Pedestrian objects.

Learning to see stuff

Textual information appearing on the captured image may contain personal information. In various circumstances, publishing such images in the public domain may create a threat of privacy leak. To avoid these situations, we propose a text concealment method. To accomplish this task, we have used a conditional generator, which is a text region conditioned concealment network. The text regions predicted by the detector network are used as a conditioning criterion for the concealment process. The text region prediction in the form of a word-level bounding box may contain stroke pixels as well as the background pixels. However, to reduce the number of background pixels for proper conditioning of text concealment network, a character level annotation is used for the generator in place of word-level bounding box annotation. It helps to focus more on strokes as compared to the background pixels. A character-level symmetric line representation of text has been proposed to obtain finer level text region prediction as compared to the character-level bounding box. The proposed model is trainable from end-to-end. The text region conditioned generator is trained from the loss of global and local discriminators. The proposed method is validated on public scene text image datasets such as ICDAR 2015, COCO-Text and Synthesis dataset. The proposed architecture shows competitive results as compared to other state-of-the-art approaches.

Appearance change of moving targets is a challenging problem in visual tracking. In this paper, we present a novel visual object tracking algorithm based on the observation dependent hidden Markov model (OD-HMM) framework. The observation dependency is computed by structure complexity coefficients (SCC) which is defined to predict the target appearance change. Unlike conventional methods addressing the appearance change problem by investigating different online appearance models, we handle this problem by addressing the fundamental reason of motion -related appearance change during visual tracking. Based on the analysis of motion-related appearance change, we investigate the relationship between the structure of the object surface and the appearance stability. The appearance of complex structural regions is easier to change compared with that of smooth structural regions with object moving. Based on this, we define SCC to predict the appearance stability of moving objects. Different from the standard HMM-based tracking algorithms where observations between different frames are assumed to be independent, we consider the observation dependency between consecutive frames with the information provided by SCC. Moreover , we present a novel outlier removing method in appearance model updating which helps to avoid error accumulation. Experimental results on challenging video sequences demonstrate that the proposed visual tracking algorithm with OD-HMM and SCC achieves better performance than existing related tracking algorithms.

Supervised object detection models are trained to recognize certain objects. These models are classified into two types: single-stage detectors and two-stage detectors. The single-stage detectors just need one pass through the model to anticipate all the bounding boxes, whereas the two-stage detectors require to first estimate the image portions where the object could be located. Due to their speed and simplicity, single-stage anchor-based models are used in many industrial settings. Training such models require bounding boxes that describe the spatial location of an object, which are usually drawn by an expert. However, the question remains, how much area should be considered when drawing the bounding boxes? In this paper, we demonstrate the effects that the size and placement of a rectangular bounding box can have on the performance of the anchor-based models. For this, we first perform experiments on a synthetically generated binary dataset and then on a real-world object detection dataset. Our results show that fixing the size of the bounding boxes can help in improving the performance of the model in the case of single class object detection (approximately 50% improvement in mAP@[.5:.95] for real world dataset). Furthermore, we also demonstrate how freely available tools can be combined for obtaining the best possible semi automated object labeling pipeline.

In order to study the issue of resource search for edge computing, a method is proposed for the first time, which can not only locating base stations within a designed region, also search for a base station locating outside the region but with a coverage overlapping the region. Mathematical model is applied to simulation of the shape and location of the region, the rectangular bounding box is used to narrow the searching scope. Moreover, the use of the ray method makes contributions to determining whether the base station in the region, and the implementation of the genetic algorithm helps to find the largest internal rectangle of the region, thus reduce the amount of calculation.