Object Detection and Tracking based on Recurrent Neural Networks

Zhang, Yashu; Ming, Yue; Zhang, Runqing

doi:10.1109/icsp.2018.8652389

Cited by 9 publications

(12 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to reduce the dependency of target detection and overcome occlusion, we propose a novel object tracking framework, called adaptive detection tracking (ADT), as shown in Figure 2. First, given an initial frame of target video, the target's motion direction of the next frame can be obtained by the direction prediction module [9]. Then, the region of interest (RoI) is determined along this direction, that is, the rough positioning of the target for adaptive detection.…”

Section: Adaptive Detection Trackingmentioning

confidence: 99%

“…It not only improves the tracking accuracy under the heavy occlusion, but also further improves the efficiency of the tracking algorithm. The adaptive detection module consists of RoI determination module proposed by our previous research [9], correlation filter module and detection module. The correlation filter module and detection module in the adaptive detection tracker will be discussed in the following subsections.…”

Section: A Adaptive Detection Mechanismmentioning

confidence: 99%

“…Therefore, the temporal information between adjacent frames should be considered to better establish the location relationship of the target to reduce the dependency on object detection and the computational cost. Our previous work [9] has already developed a direction model, which can effectively narrow down the search area of the target in the next frame. However, our previous tracker [9] based on frame-by-frame object detection significantly slowed down the tracking speed.…”

Section: Introductionmentioning

confidence: 99%

“…Our previous work [9] has already developed a direction model, which can effectively narrow down the search area of the target in the next frame. However, our previous tracker [9] based on frame-by-frame object detection significantly slowed down the tracking speed. How to realize the non-frame-by-frame adaptive detection in realtime application and avoid boundary effect and motion shift is still a problem.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

ADT: Object Tracking Algorithm Based on Adaptive Detection

Ming

Zhang

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Object tracking is one of the most fundamental and important fields in computer vision with a wide range of applications. Although great progress has been made in object tracking combined with detection, there is still enormous challenges in real-time applications and for the computer cannot effectively capture the temporal correlations of targets and background clutter. In order to improve the performance of tracking algorithms under complex unconstrained conditions, we propose a novel tracking framework based on adaptive detection, called adaptive detection tracking (ADT). First, we exploit the temporal correlation of the recurrent neural network to predict the target's motion direction and efficiently update the region of interest (RoI) in the narrow range of the next frame. Then, the algorithm utilizes the correlation filter to initialize the defined region of interest based on the threshold. If the Interaction of Union (IoU) of the predicted bounding box and the groundtruth bounding box is greater than the set threshold, the predicted bounding box will be directly output as the tracking results, whereas the detection is adaptively carried out in the determined RoI. Finally, the predicted bounding box refines the direction model as the input of the next frame to complete the whole tracking flow. Our proposed adaptive detection tracking mechanism can efficiently realize non-frame-by-frame adaptive detection with excellent tracking accuracy and is more robust in the unconstrained scenes, especially for occlusion. Comprehensive experiments demonstrate that our approach consistently achieves state-of-the-art results and runs in real-time on six large tracking benchmarks, including OTB100, VOT2016, VOT2017, TC128, UAV123 and LaSOT datasets. INDEX TERMS Recurrent neural network, adaptive detection, object tracking, correlation filtering, model compression. YUE MING received the B.S. degree in communication engineering, the M.Sc. degree in humancomputer interaction engineering, and the Ph.D. degree in signal and information processing from

show abstract

Section: Adaptive Detection Trackingmentioning

confidence: 99%

Section: A Adaptive Detection Mechanismmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

ADT: Object Tracking Algorithm Based on Adaptive Detection

Ming

Zhang

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…In particular, CNN includes other neural network models such as recurrent neural networks (RNN) and deep neural networks (DNN). These two have been used for the recognition systems in the computer vision, video processing, and image processing research areas [1][2][3][4][5][6]. Being similar to the human brain's operation in perception and recognition, the neural network algorithms are able to process given visual information to recognize the object that we target or to predict the next movement of the target object [7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Low-Power RTL Code Generation for Advanced CNN Algorithms toward Object Detection in Autonomous Vehicles

Kim

Yadav

et al. 2020

Electronics

View full text Add to dashboard Cite

In the implementation process of a convolution neural network (CNN)-based object detection system, the primary issues are power dissipation and limited throughput. Even though we utilize ultra-low power dissipation devices, the dynamic power dissipation issue will be difficult to resolve. During the operation of the CNN algorithm, there are several factors such as the heating problem generated from the massive computational complexity, the bottleneck generated in data transformation and by the limited bandwidth, and the power dissipation generated from redundant data access. This article proposes the low-power techniques, applies them to the CNN accelerator on the FPGA and ASIC design flow, and evaluates them on the Xilinx ZCU-102 FPGA SoC hardware platform and 45 nm technology for ASIC, respectively. Our proposed low-power techniques are applied at the register-transfer-level (RT-level), targeting FPGA and ASIC. In this article, we achieve up to a 53.21% power reduction in the ASIC implementation and saved 32.72% of the dynamic power dissipation in the FPGA implementation. This shows that our RTL low-power schemes have a powerful possibility of dynamic power reduction when applied to the FPGA design flow and ASIC design flow for the implementation of the CNN-based object detection system.

show abstract