IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS Editor-In-Chief

Object detection and tracking is a fundamental, challenging task in computer vision because of the difficulties in tracking. Continuous deformation of objects during movement and background clutter leads to poor tracking. In this paper, a method of multiple moving object detection and tracking by combining background subtraction and K-means clustering is proposed. The proposed method can handle objects occlusion, shadows and camera jitter. Background subtraction filters irrelevant information, and K-means clustering is employed to select the moving object from the remaining information, and it is capable of handling merging and splitting of moving objects using spatial information. Experimental results show that the proposed method is robust when compared to other techniques.

Efficient multiple moving object detection and tracking using combined background subtraction and clustering

Tracking multiple people in crowds is a fundamental and essential task in the multimedia field. It is often hindered by difficulties, such as dynamic occlusion between objects, cluttered background, and abrupt illumination changes. To respond to this need, in this paper, we combine deep and depth to build a stereo tracking system for crowds. The core of the system is the fusion of the advantages of deep learning and depth information, which is exploited to achieve object segmentation and improve the multiobject tracking performance in severe occlusion. More specifically, first, to obtain more accurate detection observations in the tracking system, we present a novel object-level segmentation method. This method combines the effective detection results of deep learning with depth information to obtain precise object segmentation results. Then, we integrate the segmentation results and three-dimensional (3-D) information to extract 2-D and 3-D characteristics to represent the target, and design three similarity models to realize a stereo tracking method through data association in crowds. Finally, we build a diverse stereo dataset including various challenging indoor and outdoor scenes. The comprehensive experiments verify the effective and robust tracking performance of our system in various scenarios, and the system has rich output results including segmentation results, target distance, and tracking results. Moreover, the qualitative and quantitative comparison results show that the proposed algorithm not only has good object segmentation performance but also improves the tracking performance of completely and partially occluded objects, which is superior to the tested state-of-the-art tracking approaches.

Joint Deep and Depth for Object-Level Segmentation and Stereo Tracking in Crowds

The invention relates to a training method and device of a neural network model for image processing. The method comprises that video frames adjacent in time are obtained; the neural network model output intermediate images corresponding to the video frames respectively; change of the video frames in relatively earlier time and optical flow information of the video frames in relatively later timeare obtained; and image formed by changing the intermediate image, corresponding to the video frame in relatively earlier time, according to the optical flow information is obtained; time loss betweenthe intermediate image corresponding to the video frame in relatively later time and an image after change is obtained; characteristic loss between the intermediate image and a target characteristicimage is obtained; and the neural network model is adjusted according to the time loss and the characteristic loss, the step of obtaining the video frames adjacent in time is returned to, and trainingis not stopped until the neural network model satisfies a training ending condition. Thus, the neural network model obtained by training has a better video characteristic conversion effect.

Training method and device of neural network model for image processing

Object detection and tracking is a field of research that has many applications in the current generation with increasing number of cameras on the streets and lower cost for Internet of Things(IoT). In this paper, a traffic intensity monitoring system is implemented based on the Macroscopic Urban Traffic model is proposed using computer vision as its source. The input of this program is extracted from a traffic surveillance camera which has another program running a neural network classification which can identify and differentiate the vehicle type is implanted. The neural network toolbox is trained with positive and negative input to increase accuracy. The accuracy of the program is compared to other related works done and the trends of the traffic intensity from a road is also calculated. relevant articles in literature searches, great care should be taken in constructing both. Lastly the limitation and the future work is concluded.

https://iopscience.iop.org/article/10.1088/1757-899X/260/1/012009/pdf

Traffic intensity monitoring using multiple object detection with traffic surveillance cameras

In video surveillance the moving object detection and tracking are important research area of computer vision. Tracking moving objects in a real time environment is not easy because of continual deformation of objects during movement. The moving item has many attributes in both temporal and spatial spaces. In the spatial area, objects vary in size while in temporal area they vary in moving speed. To track multiple object in video with optimal window size the Decomposition with Temporal Domain (DTD) is proposed. Thus the moving objects are detected and tracked until it disappears or losses it motion. The proposed strategy can identify and track objects all the while. It reduces the False Alarms Rate (FAR) and increases True Positive Rate (TPR). Moving items with various speeds and sizes are tracked with their optimal window size and the possible shadow is eliminated by the multi frame difference method. The proposed method is compared with Kalman filter and Optical Flow (OF) of Lucas-Kanade method using probabilistic approaches such as FAR and TPR performance is analyzed. Different test results have affirmed the legitimacy and adequacy of the proposed technique.

Efficient detection tracking of multiple moving objects in temporal domain

In computer vision, tracking human pose has received a growing attention in recent years. The existing methods used multi-view videos and camera calibrations to enhance the shape of the object in 3D view. In this paper, tracking and partial reconstruction of the shape of the object from a single view video is identified. The goal of the proposed integrated method is to detect the movement of a person more accurately in 2D view. The integrated method is a combination of Silhouette based pose estimation and Scene flow based pose estimation. The silhouette based pose estimation is used to enhance the shape of the object for 3D reconstruction and scene flow based pose estimation is used to capture the size as well as the stability of the object. By integrating these two poses, the accurate shape of the object has been calculated from a single view video.

L. Sindhia

Papers

Efficient detection tracking of multiple moving objects in temporal domain

Integration of poses to enhance the shape of the object tracking from a single view video