Abstract
Environmental perception is a vital feature for service robots when working in an indoor environment for a long time. The general 3D reconstruction is a low-level geometric information description that cannot convey semantics. In contrast, higher level perception similar to humans requires more abstract concepts, such as objects and scenes. Moreover, the 2D object detection based on images always fails to provide the actual position and size of an object, which is quite important for a robot’s operation. In this paper, we focus on the 3D object detection to regress the object’s category, 3D size, and spatial position through a convolutional neural network (CNN). We propose a multi-channel CNN for 3D object detection, which fuses three input channels including RGB, depth, and bird’s eye view (BEV) images. We also propose a method to generate 3D proposals based on 2D ones in the RGB image and semantic prior. Training and test are conducted on the modified NYU V2 dataset and SUN RGB-D dataset in order to verify the effectiveness of the algorithm. We also carry out the actual experiments in a service robot to utilize the proposed 3D object detection method to enhance the environmental perception of the robot.
Highlights
IntroductionThe traditional environmental perception of indoor service robots mainly solves the problems of localization, navigation, and obstacle avoidance in order to carry out autonomous movement
The traditional environmental perception of indoor service robots mainly solves the problems of localization, navigation, and obstacle avoidance in order to carry out autonomous movement.most of these studies focus on the description of the geometric information of an environment.The high-level perception of the environment for the indoor service robots requires more abstract information, such as semantic information like objects and scenes
The structure of this paper is organized as follows: Section 2 summarizes the recent research in the area of 3D object detection; Section 3 describes the proposed multi-channel convolutional neural network (CNN) for 3D object detection in detail; Section 4 presents experimental results of the algorithm; and Section 5 summarizes the content of the article
Summary
The traditional environmental perception of indoor service robots mainly solves the problems of localization, navigation, and obstacle avoidance in order to carry out autonomous movement. Fast R-CNN [5] and Faster R-CNN [6] have greatly improved the precision and efficiency of the object detection In these algorithms, a feature map is obtained through convolutional neural network and spatial pyramid pooling [7] is employed to generate the fixed dimension vector of the proposal region in the feature map. This paper proposes a multi-channel neural network system that combines the RGB, depth, and BEV images to achieve the 3D indoor object detection. The main contributions of this paper are as follows: a multi-channel convolutional neural network-based 3D object detection for indoor robot environmental perception, which combines RGB, depth, and BEV imagesas the input. The structure of this paper is organized as follows: Section 2 summarizes the recent research in the area of 3D object detection; Section 3 describes the proposed multi-channel CNN for 3D object detection in detail; Section 4 presents experimental results of the algorithm; and Section 5 summarizes the content of the article
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call