Real-time multiple object tracking in smart environments

We describe a novel probabilistic framework for real-time tracking of multiple objects from combined depth-colour imagery. Object shape is represented implicitly using 3D signed distance functions. Probabilistic generative models based on these functions are developed to account for the observed RGB-D imagery, and tracking is posed as a maximum a posteriori problem. We present first a method suited to tracking a single rigid 3D object, and then generalise this to multiple objects by combining distance functions into a shape union in the frame of the camera. This second model accounts for similarity and proximity between objects, and leads to robust real-time tracking without recourse to bolt-on or ad-hoc collision detection.

Efficient and accurate object detection, classification and tracking have played a very important role in the advancement of computer vision systems. With the rise of deep learning techniques, the accuracy of visioning systems has increased a lot. This proposed work targets to incorporate state-of-the-art technology with the aim of achieving very high accuracy for real-time multiclass multiple object tracking with occlusion handling. A real-time multiclass multiple object tracker (MOT) is proposed using state-of-the-art object detection framework and deep convolutional neural networks. The proposed model is developed using YOLOv3 architecture for object detection and for real-time tracking, and a longer period of occlusion handling simple online and real-time tracking (SORT) is used as a base algorithm. The velocity and acceleration of objects along with their appearance information are used to predict the object location upon occlusion. Later detections are compared with MOT dataset detections and the YOLO bounding boxes, and based on their IOU matrix, normalized detections are provided.

Real-time tracking of multiple objects in space-variant vision based on magnocellular visual pathway

Real time and accrual object tracking is ultimate aim of a visual tracker. Recently mean shift object tracking algorithm is studied in an all-round way and utilized to visual tracking in both civil and military fields. Compared to the traditional mean shift algorithm and its other versions distance weight mean shift algorithm can effectively improve the precision and robustness. It analyzes the dissimilarity of target feature color histogram with distance weight and candidate area feature color histogram with distance weight to calculate mean shift vector, and searches for target area via each iteration in candidate area. Though improved on basis of traditional mean shift algorithm, there are a large amount of calculations and the processing speed has already been a bottleneck in real time object tracking. Graphics processor unit (GPU) has special hardware parallel computing resources and has been already employed in various embedded systems. It provides us with an alternative implementation on GPU which can solve such bottleneck problem. The paper proposes a way of implementation of distance weight mean shift algorithm on GPU. The experiment results show that the execution performance of the implementation on GPU is over 56 times speedup of that completely on CPU at most, and can meet the requirement of real time and accuracy.

In this paper, we present a robust approach to real-time tracking of multiple objects in mediated environments using a set of calibrated color and IR cameras. Challenges addressed in this paper include robust object tracking in the presence of color projections on the ground plane and partial/complete occlusions. To improve tracking in such complex environment, false candidates introduced by ground plane projection or mismatching of objects between views are removed by using the epipolar constraint and the planar homography. A mixture of Gaussian is learned using the expectation-maximization algorithm for each target to further refine the 3D location estimates. Experimental results demonstrate that the proposed approach is capable of robust and accurate 3D object tracking in a complex environment with a great amount of visual projections and partial/complete occlusions.

Recently, because of its importance in computer vision and surveillance systems, object tracking has progressed rapidly. In this paper a novel strategy for tracking multiple objects using static cameras is introduced, which can be used to grant a cheap, easy installation, and robust tracking system. The proposed tracking strategy is based on scenes captured by static video cameras. Each camera is attached to a workstation that analyses its stream. All workstations are connected to a tracking server, which harmonises the system, collects the data, and creates the output spatial–tempo database. Our contribution comes in two issues. The first is to present a new methodology for transforming the image coordinates of an object to its real coordinates. The second is to offer a flexible event–based object tracking strategy, which has been tested over a CAD of soccer game environment. Preliminary experimental results show the robust performance of the proposed tracking strategy.

Tracking is a major issue of virtual and augmented reality applications. Single object tracking on monocular video streams is fairly well understood. However, when it comes to multiple objects, existing methods lack scalability and can recognize only a limited number of objects. Thanks to recent progress in feature matching, state-of-the-art image retrieval techniques can deal with millions of images. However, these methods do not focus on real-time video processing and cannot track retrieved objects. In this paper, we present a method that combines the speed and accuracy of tracking with the scalability of image retrieval. At the heart of our approach is a bi-layer clustering process that allows our system to index and retrieve objects based on tracks of features, thereby effectively summarizing the information available on multiple video frames. Dynamic learning of new viewpoints as the camera moves naturally yields the kind of robustness and reliability expected from an augmented reality engine. As a result, our system is able to track in real-time multiple objects, recognized with low delay from a database of more than 300 entries. We released the source code of our system in a package called Polyora.

We propose a feature-based multi-target tracking algorithm which can track multiple targets in real time with a simple but efficient velocity segmentation method. The optical flow velocity distribution profile of the feature points detected on a moving target or on the background when the camera has ego-motion is assumed to have a Gaussian-like function. We can separate the background feature points and those of moving targets by examining the velocity distribution function profile at each frame without a prior knowledge on the number and texture of the moving objects. The optical flow velocity of a feature point in each image frame is computed by the iterative Lucas-Kanade algorithm. These feature points are divided into groups with the similar velocity. Feature points are further divided into sub-groups according to their proximity the image frame. The feature point group with the largest span is identified as the background feature and its velocity is the camera velocity when the background is fixed. Multiple targets are identified based on their velocities and proximity in one frame. With a pyramidal sampling scheme to reduce the frame size to one-sixteenth of its original size, and the iterative Lucas-Kanade algorithm to find the optical flow in a multi-resolution manner, we are able to track multiple objects in real time with a moving hand-held camera.

Multiple objects following is a challenge in the area of computer vision, which is continuously gaining popularity for civilian and military purposes. However, there currently exists no baseline to apply real-time multiple objects following a system in Unmanned Aerial System (UAV). Therefore, this paper proposes a real-time following system aiming to keep all the aerial and ground objects in sight of a monocular camera, which is fixed on a UAV. This system applies tracking-by-detection architecture, where YOLO V5s, a model based on Convolutional Neural Network (CNN), is utilized for Object Detection whereas the SORT algorithm is used for Object Tracking. Furthermore, a visual servo controller is designed to control the UAV to complete the tracking tasks autonomously. Finally, three experiments are carried out in a simulator, where the proposed system is proved to be capable of handling multiple objects following problems within a given condition.

Multiple objects tracking is a challenging task. This article presents an algorithm which can detect and track multiple objects, and update target model automatically. The contributions of this paper as follow: Firstly,we also use color histogram(CH) and histogram of orientated gradients(HOG) to represent the objects, model update is realized by kalman filter and gaussian model; secondly we use Gaussian Mixture Model(GMM) and Bhattacharyya distance to detect object appearance. Particle filter with combined features and model update mechanism can improve tracking results. Experiments on video sequences demonstrate that the method presented in this paper can realize multiple objects detection and tracking.

This paper presents an investigation of the development of a real-time object tracking system that utilizes computer vision techniques and incorporates pan-tilt control mechanisms. The system architecture includes hardware components such as a camera and a pan-tilt mechanism, and software components such as object detection and tracking algorithms. To achieve efficient and accurate tracking, the Kalman filter, which uses a state-space model, was included in the object tracking process. The proposed system is implemented and evaluated through experiments to demonstrate its feasibility and effectiveness in real-world scenarios. The results indicate that the proposed system is capable of achieving real-time and accurate object tracking, demonstrating its potential for practical applications in various fields.

Real-time tracking of multiple objects using adaptive correlation filters with complex constraints

Real-time detection and tracking for fast moving object has important applications in various fields. However, available methods, especially low-cost ones, can hardly achieve real-time and long-duration object detection and tracking. Here we report an image-free and cost-effective method for detecting and tracking a fast moving object in real time and for long duration. The method employs a spatial light modulator and a single-pixel detector for data acquisition. It uses Fourier basis patterns to illuminate the target moving object and collects the resulting light signal with a single-pixel detector. The proposed method is able to detect and track the object with the single-pixel measurements directly without image reconstruction. The detection and tracking algorithm of the proposed method is computationally efficient. We experimentally demonstrate that the method can achieve a temporal resolution of 1,666 frames per second by using a 10,000 Hz digital micro-mirror device. The latency time of the method is on the order of microseconds. Additionally, the method acquires only 600 bytes of data for each frame. The method therefore allows fast moving object detection and tracking in real time and for long duration. This image-free approach might open up a new avenue for spatial information acquisition in a highly efficient manner.

In this paper, we propose detection based simplified multiple object tracking model with handling stationary object detection and occlusion problem for real-time intelligent surveillance system. In order to solve detection of slow and stationary object problem in Gaussian Mixture Model(GMM) based adaptive background model, we presents controlling learning rate mechanism using tracked region information. And, the simple primitive multi-features are applied for real-time multiple object tracking. As well, we proposed modified moving average filter for predicting next position of moving object to handle occlusion problems. Computational and real-target experiment results show that the proposed model can successfully track moving object within 45ms per frame for 640×480 image size on Intel® Core(TM) i7 CPU 1.6GHz in a real indoor scene including occlusion situation.

In real time object tracking is an important task in various surveillance application. Nowadays, surveillance system very common in offices, collage campus, shopping malls etc. In this paper, an automated video surveillance system presented. Althrough tracking and counting system are commercially available today; there is need for further reaserach to address the challenges of real world scenarios. There is lot of surveillance cameras installed around us but there are no means to monitor all of them continuously. It is necessary to develop a computer vision based technologies that automatically process those images in order to detect situations or unusual behavior. In order to solve the problem of poor real time tracking performance using convolutional neural network. This paper proposes a fast and accurate real time video detection and tracking algorithm. Keyword: - Video surveillance system, Moving object detection, Tracking, Background subtraction. I. Introduction Real time human body detection and tracking in indoor environment deals with the concept of higher level application of image processing and computer vision. The following key components of identify to path of real time tracking are extracting a feature, background image subtraction. If two similar color objects come to close the tracker of one object can jump to associated object. The problem is called hijacking problem. Drifting problem occur when an object abruptly changes its direction to reverse. In that case it’s become very difficult to track the object because the motion model does not work. An object tracking can be understood as the problem of finding the path (i.e. Trajectory).