Real-time multitarget tracking for sensor-based sorting

Abstract

Utilizing parallel algorithms is an established way of increasing performance in systems that are bound to real-time restrictions. Sensor-based sorting is a machine vision application for which firm real-time requirements need to be respected in order to reliably remove potentially harmful entities from a material feed. Recently, employing a predictive tracking approach using multitarget tracking in order to decrease the error in the physical separation in optical sorting has been proposed. For implementations that use hard associations between measurements and tracks, a linear assignment problem has to be solved for each frame recorded by a camera. The auction algorithm can be utilized for this purpose, which also has the advantage of being well suited for parallel architectures. In this paper, an improved implementation of this algorithm for a graphics processing unit (GPU) is presented. The resulting algorithm is implemented in both an OpenCL and a CUDA based environment. By using an optimized data structure, the presented algorithm outperforms recently proposed implementations in terms of speed while retaining the quality of output of the algorithm. Furthermore, memory requirements are significantly decreased, which is important for embedded systems. Experimental results are provided for two different GPUs and six datasets. It is shown that the proposed approach is of particular interest for applications dealing with comparatively large problem sizes.

Experimental Evaluation of a Novel Sensor-Based Sorting Approach Featuring Predictive Real-Time Multiobject Tracking

“…For instance, the Kalman filter update steps can be performed concurrently for all objects that are currently being tracked. Also, we use the optimized Auction Algorithm proposed in [48] for solving the linear assignment problem that is designed for running on a GPU and is particularly fast due to the usage of optimized data structures. The results presented in [48] show that the algorithm is capable of solving the association problem for about 1000 objects at around 200 Hz on a modern GPU.…”

“…Also, we use the optimized Auction Algorithm proposed in [48] for solving the linear assignment problem that is designed for running on a GPU and is particularly fast due to the usage of optimized data structures. The results presented in [48] show that the algorithm is capable of solving the association problem for about 1000 objects at around 200 Hz on a modern GPU. The algorithm is further robust against missed and faulty detections, which may be caused by occlusions, collisions are poor objects detection.…”

Moving Object Detection Technology of Line Dancing Based on Machine Vision

“…When the initial background image is obtained, the appropriate number of frames should be selected for modeling. If the number of selected frames is too small, holes will appear in the results obtained by the average method [18]. If it chooses too many frames, it will not only waste resources but also increase the burden of calculation.…”

Automatic Tracking Method of Basketball Flight Trajectory Based on Data Fusion and Sparse Representation Model

“…Firstly, the data of the high-resolution basketball flight appearance model are processed by data fusion technology. e data fusion method used is D-S evidence theory [27], that is, divide the evidence set, use the divided part to make independent judgment on the identification framework, and then use the Dempster rule to recombine the previously divided parts. e combination rules are as follows:…”