Object proposal using 3D point cloud for DRC-HUBO+

We present an object proposal method which utilizes the 3D data obtained from a depth sensor as well as the color information of images. Our object proposal method is designed to improve the performance of the object detection for a mobile robot equipped with a camera and a laser scanner. Compared to traditional object proposal methods using only 2D images, the proposed method provides much less number of candidate windows for object detection. We show less than 100 object proposal windows per image using the proposed method result in high recall tested on the public dataset. Our method presents object proposals in 3D space as well as in 2D image thus it can further be applied to following tasks for mobile robots such as 3D location and pose estimation of the target object after successful object detection. We validate our method using the real-world object detection dataset for outdoor mobile robots captured during the DRC Finals 2015 and the public dataset for comparison with the previous methods.

Authors

• Seunghak Shin
• Inwook Shim
• Jiyung Jung
• Yunsu Bok
• Jun-Ho Oh
• In-So Kweon

Keywords

• Proposals
• Three-dimensional displays
• Robot sensing systems
• Cameras
• Object detection
• Image color analysis
• Point Cloud
• 3D Point
• Object Proposals
• Detection Performance
• Public Datasets
• 2D Images
• 3D Space
• Object Location
• 3D Data
• Local Estimates
• Real-world Datasets
• Target Object
• Depth Camera
• 3D Position
• High Recall
• Mobile Robot
• Color Information
• Human Pose Estimation
• Objective Estimates
• Number Of Proposals
• Image Object
• RGB-D Data
• Intersection Over Union
• Clusters Of Points
• Depth Data
• Nodes In The Graph
• True Objective
• RGB-D Dataset
• Bounding Box