Improving CNN-based Planar Object Detection with Geometric Prior Knowledge

TL;DR

This paper introduces a novel image rectification method using geometric prior knowledge to improve CNN-based planar object detection, reducing training data needs and enhancing accuracy for mobile robots with RGB-D sensors.

Contribution

It presents the first image rectification approach for CNN-based object detection and provides a new RGB-D hazmat sign dataset with source code.

Findings

Significant boost in detection performance after rectification.

Reduction in required training images for effective detection.

First public hazmat sign dataset with RGB-D sensors.

Abstract

In this paper, we focus on the question: how might mobile robots take advantage of affordable RGB-D sensors for object detection? Although current CNN-based object detectors have achieved impressive results, there are three main drawbacks for practical usage on mobile robots: 1) It is hard and time-consuming to collect and annotate large-scale training sets. 2) It usually needs a long training time. 3) CNN-based object detection shows significant weakness in predicting location. We propose an improved method for the detection of planar objects, which rectifies images with geometric information to compensate for the perspective distortion before feeding it to the CNN detector module, typically a CNN-based detector like YOLO or MASK RCNN. By dealing with the perspective distortion in advance, we eliminate the need for the CNN detector to learn that. Experiments show that this approach significantly boosts the detection performance. Besides, it effectively reduces the number of training images required. In addition to the novel detection framework proposed, we also release an RGBD dataset and source code for hazmat sign detection. To the best of our knowledge, this is the first work of image rectification for CNN-based object detection, and the dataset is the first public available hazmat sign detection dataset with RGB-D sensors.