Temporal object detection has attracted significant attention, but most popular detection methods can not leverage the rich temporal information in video or robotic vision. Although many different algorithms have been developed for video detection task, real-time online approaches are frequently deficient. In this paper, based on attention mechanism and convolutional long short-term memory (ConvLSTM), we propose a temporal single-shot detector (TSSD) for robotic vision. Distinct from previous methods, we take aim at temporally integrating pyramidal feature hierarchy using ConvLSTM, and design a novel structure including a high-level temporal unit as well as a low-level one (HL-TU) for multi-scale feature maps. Moreover, we develop a creative temporal analysis unit, namely, attention-aware ConvLSTM (AC-LSTM), in which a temporal attention module is specially tailored for background suppression and scale suppression while ConvLSTM temporally integrates attention-aware features. An association loss is designed for temporal coherence. Finally, our method is evaluated on ImageNet VID dataset. Extensive comparisons on the detection capability confirm or validate the superiority of the proposed approach. Consequently, the developed TSSD is fairly faster and achieves an overall competitive performance in terms of mean average precision. As a temporal, real-time, and online detector, TSSD is applicable to robot's intelligent perception.
View on arXiv