Camera Parameters Aware Motion Segmentation Network with Compensated Optical Flow

Learning to distinguish independent moving objects from the observed optical flow with a moving camera remains challenging. In this work, we first present a novel camera pose compensation (CPC) scheme. With the help of ingenious geometric analysis, it breaks the observed optical flow into patterns that are easier to interpret for the motion segmentation network. Secondly, we further refine such compensation with a camera parameter aware (CPA) module to account for poses’ errors in the CPC processing and enhance the entire network’s tolerance to noises. Additionally, an MMPNet is developed to intensify the identification ability of overall motion patterns. It reaches a larger receptive field with a bottom-up information transmission structure and integrates motion information at different granularities. We demonstrate the benefits of our framework on FlyingThings3D and Monkaa datasets. Without the complement of semantic information, our approach outperforms the top methods for moving objects segmentation.

Authors

• Xianshun Wang
• Dongchen Zhu
• Shaojie Xu
• Wenjun Shi
• Yanqing Liu
• Jiamao Li
• Xiaolin Zhang

Keywords

• Computer vision
• Image motion analysis
• Motion segmentation
• Semantics
• Object segmentation
• Information processing
• Cameras
• Optical Flow
• Receptive Field
• Motion Patterns
• Geometric Analysis
• Camera Pose
• Triangulation
• Basic Information
• Flow Field
• Motion Detection
• 3D Coordinates
• Consecutive Frames
• Intrinsic Parameters
• Residual Vector
• Multilevel Structure
• Dilated Convolution
• Saliency Map
• Local Motion
• Camera Motion
• Original Pixel
• Extrinsic Parameters
• Scene Structure
• Camera Movement
• Camera Intrinsic Parameters
• Projection Error
• Complete Compensation
• Forward Flow
• Feature Maps
• RGB Images
• Classical Methods
• Electromagnetic Field