Joint 3D Proposal Generation and Object Detection from View Aggregation

6 Dec 2017Jason KuMelissa MozifianJungwook LeeAli HarakehSteven Waslander

We present AVOD, an Aggregate View Object Detection network for autonomous driving scenarios. The proposed neural network architecture uses LIDAR point clouds and RGB images to generate features that are shared by two subnetworks: a region proposal network (RPN) and a second stage detector network... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Birds Eye View Object Detection KITTI Cars Easy AVOD-FPN AP 88.53 # 5
3D Object Detection KITTI Cars Easy AVOD + Feature Pyramid AP 81.94% # 11
Object Detection KITTI Cars Easy AVOD-FPN AP 81.94 # 4
3D Object Detection KITTI Cars Hard AVOD + Feature Pyramid AP 66.38% # 9
Object Detection KITTI Cars Hard AVOD-FPN AP 66.38 # 3
3D Object Detection KITTI Cars Moderate AVOD + Feature Pyramid AP 71.88% # 13
Birds Eye View Object Detection KITTI Cars Moderate AVOD-FPN AP 83.79% # 5
Object Detection KITTI Cars Moderate AVOD-FPN AP 71.88 # 4
3D Object Detection KITTI Cyclists Easy AVOD + Feature Pyramid AP 64.00% # 9
3D Object Detection KITTI Cyclists Hard AVOD + Feature Pyramid AP 46.61% # 9
Birds Eye View Object Detection KITTI Cyclists Moderate AVOD-FPN AP 57.48% # 5
3D Object Detection KITTI Cyclists Moderate AVOD + Feature Pyramid AP 52.18% # 9
3D Object Detection KITTI Pedestrians Easy AVOD + Feature Pyramid AP 50.80% # 6
3D Object Detection KITTI Pedestrians Hard AVOD + Feature Pyramid AP 40.88% # 5
Birds Eye View Object Detection KITTI Pedestrians Moderate AVOD-FPN AP 51.05% # 2
3D Object Detection KITTI Pedestrians Moderate AVOD + Feature Pyramid AP 42.81% # 6

Methods used in the Paper