Gaussian Mixture Model (GMM) Based Dynamic Object Detection and Tracking

This paper presents a novel approach for reactive obstacle avoidance for static and dynamic objects using monocular image sequences. A sparse motion field is calculated by tracking point features using the Kanade-Lucas-Tomasi method. The rotational component of this sparse optical flow due to ego motion of the camera is compensated using motion parameters estimated directly from the images. A robust method for detection of static and dynamic objects in the scene is applied to identify collision candidates. The approach operates entirely in the image space of a monocular camera and does not require any extrinsic information about the configuration of the sensor or speed of the camera. The system prioritizes the detected collision candidates by their time to collision. Additionally, the spatial distribution of the candidates is calculated for non-degenerated conditions. We present the mathematical framework and the experimental validation of the suggested approach on simulated and real-world data.

Real-time motion planning in an unknown environment involves collision avoidance of static as well as moving agents. Strategies suitable for navigation in a stationary environment cannot be translated as strategies per se for dynamic environments. In a purely stationary environment all that the sensor can detect can only be a static object is assumed implicitly. In a mixed environment such an assumption is no longer valid. For efficient collision avoidance identification of the attribute of the detected object as static or dynamic is probably inevitable. Presented here are two novel schemes for perceiving the presence of dynamic objects in the robot's neighborhood. One of them, called the Model-Based Approach (MBA) detects motion by observing changes in the features of the environment represented on a map. The other CBA (cluster-based approach) partitions the contents of the environment into clusters representative of the objects. Inspecting the characteristics of the partitioned clusters reveals the presence of dynamic agents. The extracted dynamic objects are tracked in consequent samples of the environment through a straightforward nearest neighbor rule based on the Euclidean metric. A distributed fuzzy controller avoids the tracked dynamic objects through direction and velocity control of the mobile robot. The collision avoidance scheme is extended to overcome multiple dynamic objects through a priority based averaging technique (PBA). Indicating the need for additional rules apart from the PBA to overcome conflicting decisions while tackling multiple dynamic objects can be considered as another contribution of this effort. The method has been tested through simulations by navigating a sensor-based mobile robot amidst multiple dynamic objects and its efficacy established.

Using remote sensing data for marine monitoring, marine rescue, marine pollution monitoring which has a broad monitoring area and fast response time, so in the last 10 years, satellite borne or airborne optical and SAR sensor data have been increasingly used in the field of ocean monitoring. However, based on the dynamic video to carry out the study of the detection of irregular debris blocks from the wrecked ship, aircraft is less. To a great extent, it affects the efficiency of maritime rescue. This paper, based on the dynamic objects detection, Color Space Quantization and property of Human Vision System, takes the irregular wreckage patches as research. And a detection algorithm for dynamic objects is developed with the foundation of Lab channels. To verify that, the calculation of the Euclidean distance between the characteristic parameters of irregular wreckage patches and regular floating ones, and the average Euclidean distance is 0.8245 between the irregular1 and the regular while that between irregular2 and the regular is 4.3645. At the same time, the Hausdorff distance was calculated and verified, and the average distance between the irregular block 1 and the regular block was 2.5975. The average distance between the block 2 and the rule block was 13.8962. Experimental results show that the method is consistent with the results of the second methods, which proves that the first method is scientific and operational. Therefore, it can be found that some parameters including divergence, elongation and eccentricity fluctuate dramatically from those in irregular ones to the regular one, which could be extracted to recognize or distinguish the patches. That is why this paper is of importance in marine rescue and detection of objects on the sea surface.

In a typical railyard environment, a myriad of large and dynamic objects pose significant risks to railyard workers. Unintentional falls, trips and collisions with dynamic rolling stock due to distractions or lack of situational awareness are an unfortunate reality in modern railyards. The challenges of current technologies in detecting and tracking multiple differently-sized mobile objects in situations such as i) one-on-one, ii) many-to-one, iii) one-to-many, iv) blind spot, and v) interfering/non-interfering separation creates the possibility for reduction or loss of situational awareness in this fast-paced environment. The simultaneous tracking of assets with different size, velocity and material composition in different working and environmental conditions can only be accomplished through joint infrastructure-based asset discovery and localization sensors that cause no interference or impediment to the railyard workers, and which are capable of detecting near-misses as well. Our team is investigating the design and performance of such a solution, and is currently focusing on the innovative usage of lightweight low-cost RADAR under different conditions that are expected to be encountered in railyards across North America. We are employing Ancorteks 580-AD Software Defined RADAR (SDRadar) system, which operates at the license-free frequency of 5.8 GHz and with a variety of different configuration options that make it well-suited for generalized object tracking. The challenges, however, stem from the unique interplay between tracking large metallic objects such as railcars, locomotives, and trucks, as well as smaller objects such as railyard workers, in particular their robust discernment from each other. Our design’s higher-level system can interact with the lower-level SDRadar design to change the parameters in real-time to detect and track large objects over significant distances. The algorithm optimally adjusts waveform, sweep time and sample rate based on one or multiple detected object cross-sections and subsequently alters these parameters to be able to discern other objects from them that are in close proximity. We also use an ensemble method to determine the velocity and distance of target objects to accurately track the subject and larger objects at a distance. The methodology has been field-tested with several test cases in a multitude of weather and lighting conditions. We have also tested the proper height, azimuth and elevation angles for positioning our SDRadar to alleviate the risk of blind spots and enhancing the detection and tracking capabilities of our algorithm. The approach has outperformed our previous tests using visual and acoustic sensors for detection and tracking railroad workers in terms of accuracy and operating flexibility. In this paper, we discuss the details of our proposed approach and present our results from the field tests.

This paper proposes a visual-inertial navigation system (VINS) combined with a dynamic object detection (DOD) algorithm, to improve the localization and state estimate accuracy of autonomous driving vehicles (ADV) in dynamic environments. Firstly, based on the YOLOv5 network, we train the proposed DOD model to detect dynamic objects in the road environment. Secondly, by removing the feature points in the dynamic object regions, we track the remaining feature points to eliminate the influence of the dynamic object. Furthermore, we model the global positioning system (GPS) measurement as a general factor and introduce its residual factor into the cost function to eliminate the cumulative error. Finally, we validate the performance of the proposed method on public datasets and real-world experiments. The results show that the proposed method can effectively eliminate the influence of the dynamic object and eliminate the cumulative error. It provides theoretical guidance for ADV navigation in dynamic or large-scale outdoor environments.

Object detection algorithms using convolutional neural networks (CNNs) achieve high detection accuracy, but it is challenging to realize real-time object detection due to their high computational complexity, especially on resource-constrained mobile platforms. In this article, we propose an algorithm-hardware co-optimization approach to designing a real-time object detection system. We first develop a compact object detection model based on a binarized neural network (BNN), which employs a new layer structure, the DenseToRes layer, to mitigate information loss due to deep quantization. We also propose an efficient object detection processor that runs object detection with high throughput using limited hardware rescources. We develop a resource-efficient processing unit supporting variable precision with minimal hardware overheads. Implemented in field-programmable gate array (FPGA), the object detection processor achieves 64.51 frames/s throughput with 64.92 mean average precision (mAP) accuracy. Compared to prior FPGA-based designs for object detection, our design achieves high throughput with competitive accuracy and lower hardware implementation costs.

The paper presents review of key aspects associated with object detection and tracking algorithms in sensing systems for automotive applications covering active safety, advanced driver assistance and autonomous driving systems. The role of discussed systems is to establish location and monitor relative movement of objects and environment with main focus on identification of vulnerable road users. The object detection algorithms allow to classify and differentiate both static and dynamic objects in the vehicle’s surrounding. The analysis will be focused on selection of most suitable platform for development of optimized and safe vulnerable road user detection system.

Detection and tracking of on-road moving objects are crucial for vehicle perception. Data Fusion of perception sensors like cameras, lidar, and radar, allows the automotive perception to achieve a certain level of robustness and performance. The efficiency of vehicle perception determines its accuracy to take better decisions related to road safety. In this article, we propose two approaches for the detection and tracking of on-road moving objects by combining information from lidar and radar sensors. In this work, we propose to use a probabilistic occupancy grid for sensor fusion of radar and lidar point cloud, and a modified YOLO DeepSORT approach to detect, classify, and track the moving objects. Using both traditional and deep learning approaches, data fusion allows us to improve the robustness of the automotive perception pipeline. We finally used the nuScenes dataset to evaluate and compare the accuracy of our approaches with state-of-the-art trackers and detectors. We achieved an AMOTA score of 68.3% and a mAP score of 68.7% for the tracking and detection tasks respectively.

In several applications of computer vision and image processing, the inception of the processing starts with object detection and subsequently tracking, if the need arises. In recent years, there has been extensive research in the field of object detection and tracking. Many remarkable algorithms have been developed for object detection and tracking, including color segmentation, edge tracking and many more. However, all these algorithms faced the limited success in their implementation in the real world and were also bounded by the constraints such as white/plain background. This paper is the result of our research where our research team developed and implemented object detection and tracking system operational in an unknown background, using real-time video processing and a single camera. The proposed system has been extensively tested to operate in complex, real world, non-plain, light variant, changing background.

Object detection is a major branch and fundamental task in computer vision, aiming to localize, identify and classify even the smallest objects of interest in images. Features can be extracted efficiently by deep convolutional neural networks (CNNs) as the backbone for real-time or near real-time object detection performance than the hand-crafted-based traditional methods. In the past few years, the advent of transformer-based models with robust self-attention mechanisms has not only raised object detection performance to a higher level but has also enabled it to produce excellent results. Many object detection tasks in the real world require that 3D information about the object be obtained, thus strengthening active research in 3D object detection. However, the algorithms for detecting 3D objects are not easy to propagate in real-world applications due to many factors, making reconstruction of 2D object detection algorithms to 3D object detection algorithms the suitable alternative. Therefore, we review the evolution of 2D object detection algorithms for digital imaging applications, focusing on their developments, models, applications, datasets, evaluation metrics, strengths and weaknesses, for better understanding of their landmarks and contributions to the advancement of the field.

This paper proposes a Blended Reality Agent called "BReA" that can exist in both the real and virtual world and has communicative advantages that is more than simply the sum of those of a robotic agent and an on-screen agent. BReA can seamlessly transfer between the real world and virtual world and users can communicate with BReA without interruption during the transference. We conducted a field test and showed that users can recognize when it points from the virtual world to a real world object after it moves from the real world to virtual world. This result supports a hypothesis that communicating with BReA helps users recognize the link between real world and virtual world objects and virtual world information.

Real-time object detection and tracking in video streams has become a fundamental component of modern intelligent systems, enabling applications in surveillance, autonomous driving, robotics, healthcare monitoring, and smart cities. The rapid advancement of deep learning techniques has significantly improved the accuracy and efficiency of detecting and tracking multiple objects under complex and dynamic environments. This study presents a deep learning–based framework for real-time object detection and tracking in continuous video streams, emphasizing both computational efficiency and detection robustness.The proposed system integrates a state-of-the-art convolutional neural network (CNN)-based object detector with a reliable multi-object tracking algorithm. The detection module identifies objects of interest in each frame, while the tracking component maintains consistent identities across consecutive frames by utilizing motion prediction and feature association strategies. To achieve real-time performance, the model is optimized through lightweight network architectures and parallel processing on GPU hardware. Data augmentation and transfer learning techniques are employed to enhance generalization and reduce training time. Performance evaluation is conducted on benchmark video datasets using standard metrics such as precision, recall, mean Average Precision (mAP), and tracking accuracy. Experimental results demonstrate that the proposed framework achieves high detection accuracy while maintaining low latency, making it suitable for real-time deployment. Furthermore, the system effectively handles challenges such as occlusion, scale variation, and illumination changes. This research presents a comprehensive study on real-time object detection and tracking in video streams using deep learning techniques. The proposed framework integrates YOLO-based object detection with Deep SORT multi-object tracking to achieve robust spatial localization and temporal identity preservation. The study evaluates performance using benchmark datasets including COCO, MOT17, and KITTI. Mathematical formulations of detection loss, Kalman filtering, and data association are presented. Experimental analysis using precision, recall, mAP, MOTA, ROC-AUC, and PR-AUC demonstrates that the system achieves high detection accuracy while maintaining real-time performance above 35 frames per second. The findings confirm that deep learning-based frameworks provide scalable and efficient solutions for surveillance, autonomous vehicles, and intelligent monitoring systems.

This paper describes CPU Based YOLO, a real time object detection model to run on Non-GPU computers that may facilitate the users of low configuration computer. There are a lot of well improved algorithms for object detection such as YOLO, Faster R-CNN, Fast R-CNN, R-CNN, Mask R-CNN, R-FCN, SSD, RetinaNet etc. YOLO is a Deep Neural Network algorithm for object detection which is most fast and accurate than most other algorithms. YOLO is designed for GPU based computers which should have above 12GB Graphics Card. In our model, we optimize YOLO with OpenCV such a way that real time object detection can be possible on CPU based Computers. Our model detects object from video in 10.12 - 16.29 FPS and with 80-99% confidence on several Non -GPU computers. CPU Based YOLO achieves 31.05% mAP.

In practice, the object detection algorithm is limited by a complex detection environment, hardware costs, computing power, and chip running memory. The performance of the detector will be greatly reduced during operation. Determining how to realize real-time, fast, and high-precision pedestrian recognition in a foggy traffic environment is a very challenging problem. To solve this problem, the dark channel de-fogging algorithm is added to the basis of the YOLOv7 algorithm, which effectively improves the de-fogging efficiency of the dark channel through the methods of down-sampling and up-sampling. In order to further improve the accuracy of the YOLOv7 object detection algorithm, the ECA module and a detection head are added to the network to improve object classification and regression. Moreover, an 864 × 864 network input size is used for model training to improve the accuracy of the object detection algorithm for pedestrian recognition. Then the combined pruning strategy was used to improve the optimized YOLOv7 detection model, and finally, the optimization algorithm YOLO-GW was obtained. Compared with YOLOv7 object detection, YOLO-GW increased Frames Per Second (FPS) by 63.08%, mean Average Precision (mAP) increased by 9.06%, parameters decreased by 97.66%, and volume decreased by 96.36%. Smaller training parameters and model space make it possible for the YOLO-GW target detection algorithm to be deployed on the chip. Through analysis and comparison of experimental data, it is concluded that YOLO-GW is more suitable for pedestrian detection in a fog environment than YOLOv7.

Object detection is a fundamental problem in computer vision, with applications spanning self-driving cars, surveillance systems, medical imaging, robotics, and smart cities. Among the myriad of algorithms developed for this task, the You Only Look Once (YOLO) family stands out for its ability to perform real-time and accurate object detection. This article provides a comprehensive analysis of the YOLO algorithm series, from YOLOv1 to YOLOv8, evaluating them across key performance metrics, including precision, recall, mean Average Precision (mAP), frames per second (FPS), and overall effectiveness. Unlike traditional two-stage detectors such as R-CNN, YOLO formulates object detection as a single regression problem: a single pass over the image simultaneously predicts bounding boxes and class probabilities. This end-to-end design enables YOLO to achieve high speed while maintaining a competitive accuracy-efficiency trade-off. We examine architectural innovations across YOLO versions, including batch normalization, anchor boxes, residual blocks, feature pyramid networks, and attention mechanisms, and discuss their impact on performance. Lightweight models (e.g., YOLOv5-Nano, YOLOv8-Small) are explored with a focus on their suitability for mobile and embedded systems, highlighting YOLO’s adaptability to resource-constrained environments. Challenges such as small object detection, occlusion, and domain-specific tuning are also addressed. This article serves as a practical guide for researchers, developers, and practitioners aiming to leverage YOLO for real-world object detection tasks.