Abstract
With recent advances in object detection, the tracking-by-detection method has become mainstream for multi-object tracking in computer vision. The tracking-by-detection scheme necessarily has to resolve a problem of data association between existing tracks and newly received detections at each frame. In this paper, we propose a new deep neural network (DNN) architecture that can solve the data association problem with a variable number of both tracks and detections including false positives. The proposed network consists of two parts: encoder and decoder. The encoder is the fully connected network with several layers that take bounding boxes of both detection and track-history as inputs. The outputs of the encoder are sequentially fed into the decoder which is composed of the bi-directional Long Short-Term Memory (LSTM) networks with a projection layer. The final output of the proposed network is an association matrix that reflects matching scores between tracks and detections. To train the network, we generate training samples using the annotation of Stanford Drone Dataset (SDD). The experiment results show that the proposed network achieves considerably high recall and precision rate as the binary classifier for the assignment tasks. We apply our network to track multiple objects on real-world datasets and evaluate the tracking performance. The performance of our tracker outperforms previous works based on DNN and comparable to other state-of-the-art methods.
Highlights
Multi-object tracking is of great importance in computer vision for many applications including visual surveillance [1], robotics [2], and biomedical data analysis [3]
In [24], Milan et al proposed data-driven approximations of the data association problem under recurrent neural network approach using Long Short Term Memory (LSTM) that approximates the marginal distributions of a linear assignment problem
Contributions of this paper are as follows: (1) We propose a new deep neural network that can the solve association problem with arbitrary-sized inputs; and (2) we tested the proposed multi-object tracking (MOT)
Summary
Multi-object tracking is of great importance in computer vision for many applications including visual surveillance [1], robotics [2], and biomedical data analysis [3]. In [24], Milan et al proposed data-driven approximations of the data association problem under recurrent neural network approach using Long Short Term Memory (LSTM) that approximates the marginal distributions of a linear assignment problem They tested their method with simulated scenarios and showed that their method outperformed the JPDA [25] based methods. We propose a new method based on a bi-directional LSTM that sequentially processes inputs so that it is able to handle arbitrary-size data association problems. Contributions of this paper are as follows: (1) We propose a new deep neural network that can the solve association problem with arbitrary-sized inputs; and (2) we tested the proposed MOT algorithm based on the deigned deep neural network with the real-world datasets, e.g., SDD [1] and MOTChallenge [26].
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.