Knowledge Commons of Institute of Automation,CAS
Temporally Identity-Aware SSD With Attentional LSTM | |
Chen, Xingyu1,2; Yu, Junzhi1,3; Wu, Zhengxing1,2 | |
发表期刊 | IEEE Transactions on Cybernetics |
2020-04 | |
卷号 | 56期号:6页码:2674–2686 |
摘要 | Temporal object detection has attracted significant attention, but most popular detection methods cannot leverage rich temporal information in videos. Very recently, many algorithms have been developed for video detection task, yet very few approaches can achieve real-time online object detection in videos. In this paper, based on the attention mechanism and convolutional long short-term memory (ConvLSTM), we propose a temporal single-shot detector (TSSD) for real-world detection. Distinct from the previous methods, we take aim at temporally integrating pyramidal feature hierarchy using ConvLSTM, and design a novel structure, including a low-level temporal unit as well as a high-level one for multiscale feature maps. Moreover, we develop a creative temporal analysis unit, namely, attentional ConvLSTM, in which a temporal attention mechanism is specially tailored for background suppression and scale suppression, while a ConvLSTM integrates attention-aware features across time. An association loss and a multistep training are designed for temporal coherence. Besides, an online tubelet analysis (OTA) is exploited for identification. Our framework is evaluated on ImageNet VID dataset and 2DMOT15 dataset. Extensive comparisons on the detection and tracking capability validate the superiority of the proposed approach. Consequently, the developed TSSD-OTA achieves a fast speed and an overall competitive performance in terms of detection and tracking. Finally, a real-world maneuver is conducted for underwater object |
关键词 | Object detection Sequential learning Trackingby-detection Video processing |
WOS记录号 | WOS:000536299200030 |
七大方向——子方向分类 | 机器人感知与决策 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39057 |
专题 | 复杂系统认知与决策实验室_先进机器人 |
通讯作者 | Yu, Junzhi |
作者单位 | 1.Institute of Automation, Chinese Academy of Science 2.University of Chinese Academy of Sciences 3.Peking University |
推荐引用方式 GB/T 7714 | Chen, Xingyu,Yu, Junzhi,Wu, Zhengxing. Temporally Identity-Aware SSD With Attentional LSTM[J]. IEEE Transactions on Cybernetics,2020,56(6):2674–2686. |
APA | Chen, Xingyu,Yu, Junzhi,&Wu, Zhengxing.(2020).Temporally Identity-Aware SSD With Attentional LSTM.IEEE Transactions on Cybernetics,56(6),2674–2686. |
MLA | Chen, Xingyu,et al."Temporally Identity-Aware SSD With Attentional LSTM".IEEE Transactions on Cybernetics 56.6(2020):2674–2686. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
TSSD_TCYB.pdf(4323KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论