STDnet-ST: Spatio-temporal ConvNet for small object detection

作者：

Highlights：

• STDnet-ST is a novel spatio-temporal ConvNet for small object detection.

• STDnet-ST exploits the correlation of promising regions between frames.

• An efficient tubelet linking is performed to link small objects across video frames.

• A novel tubelet suppression algorithm is proposed to avoid unprofitable tubelets.

• STDnet-ST outperforms its state-of-the-art counterparts for small target detection.

摘要

•STDnet-ST is a novel spatio-temporal ConvNet for small object detection.•STDnet-ST exploits the correlation of promising regions between frames.•An efficient tubelet linking is performed to link small objects across video frames.•A novel tubelet suppression algorithm is proposed to avoid unprofitable tubelets.•STDnet-ST outperforms its state-of-the-art counterparts for small target detection.

论文关键词：Small object detection,Spatio-temporal convolutional network,Object linking

论文评审过程：Received 19 March 2020, Revised 5 October 2020, Accepted 28 February 2021, Available online 10 March 2021, Version of Record 20 March 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.107929