TSSD: Temporal Single-Shot Object Detection Based on Attention-Aware LSTM

03/01/2018
by   Xingyu Chen, et al.
0

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.

READ FULL TEXT

page 2

page 3

page 6

page 7

page 12

research
03/01/2018

TSSD: Temporal Single-Shot Detector Based on Attention and LSTM for Robotic Intelligent Perception

Temporal object detection has attracted significant attention, but most ...
research
11/17/2017

Mobile Video Object Detection with Temporally-Aware Feature Maps

This paper introduces an online model for object detection in videos des...
research
03/14/2022

Attention based Memory video portrait matting

We proposed a novel trimap free video matting method based on the attent...
research
04/16/2018

Optimizing Video Object Detection via a Scale-Time Lattice

High-performance object detection relies on expensive convolutional netw...
research
02/21/2017

Object Detection in Videos with Tubelet Proposal Networks

Object detection in videos has drawn increasing attention recently with ...
research
03/22/2021

Temporal Feature Networks for CNN based Object Detection

For reliable environment perception, the use of temporal information is ...

Please sign up or login with your details

Forgot password? Click here to reset