Recurrent Neural Networks for video object detection

Abstract

There is lots of scientific work about object detection in images. For many applications like for example autonomous driving the actual data on which classification has to be done are videos. This work compares different methods, especially those which use Recurrent Neural Networks to detect objects in videos. We differ between feature-based methods, which feed feature maps of different frames into the recurrent units, box-level methods, which feed bounding boxes with class probabilities into the recurrent units and methods which use flow networks. This study indicates common outcomes of the compared methods like the benefit of including the temporal context into object detection and states conclusions and guidelines for video object detection networks.

References in corpus (8)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• MobileNetV2: Inverted Residuals and Linear Bottlenecks
• T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
• SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving
• Spatially Supervised Recurrent Convolutional Neural Networks for Visual Object Tracking
• Towards High Performance Video Object Detection for Mobiles
• Looking Fast and Slow: Memory-Guided Mobile Video Object Detection
• Feature Selective Small Object Detection via Knowledge-based Recurrent Attentive Neural Network