Abstract
Recently, as the demand for technological advancement in the field of autonomous driving and smart video surveillance is gradually increasing, considerable progress in multi-object tracking using deep neural networks has been achieved, and its application field is also expanding. However, various problems have not been fully addressed owing to the inherent limitations in video cameras, such as the tracking of objects in an occluded environment. Therefore, in this study, we propose a density-based object tracking technique redesigned based on DBSCAN, which has high robustness against noise and is excellent for nonlinear clustering. Moreover, it improves the noise vulnerability inherent to multi-object tracking, reduces the difficulty of trajectory separation, and facilitates real-time processing through simple structural expansion. Through performance test evaluation, it was confirmed that by using the proposed technique, several performance indices were improved compared to the existing tracking technique. In particular, when added as a post processor to the existing tracker, the tracking performance owing to noise suppression was considerably improved by more than 10%. Thus, the proposed method can be applied in industrial environments, such as real pedestrian analysis and surveillance security systems.
Highlights
Recent advances in autonomous driving, intelligent robots, and smart video surveillance systems have evidenced multi-object tracking (MOT), which aims to estimate the trajectories of multiple objects of interest identified over time in a video sequence, as one of the most important computer vision tasks [1,2]
MOT techniques have attracted attention owing to the breakthrough development of autonomous driving and smart video surveillance systems
The main approach developed for tracking is a paradigm that identifies objects based on deep neural networks (DNNs) and tracks objects by analyzing the target identity in a video
Summary
Recent advances in autonomous driving, intelligent robots, and smart video surveillance systems have evidenced multi-object tracking (MOT), which aims to estimate the trajectories of multiple objects of interest identified over time in a video sequence, as one of the most important computer vision tasks [1,2]. Various similarity models have been proposed, such as modifying the convolutional neural network (CNN) structure [22,23] or vector embedding through fusion with long short-term memory [24,25], many studies still use feature vectors and graph models extracted through reidentification-based CNN [26,27] They have higher robustness than graph models in an environment where temporal occlusion or noise exists, but vast amounts of data must be secured for learning. We propose a density-based tracklet association annealer (DTAA)—a novel tracking-by-detection technique This technique aims to improve the vulnerability to noise and difficulty of trajectory separation inherent to MOT and to secure real-time processing through simple structural expansion.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
