Online self-supervised multi-instance segmentation of dynamic objects

This paper presents a method for the continuous segmentation of dynamic objects using only a vehicle mounted monocular camera without any prior knowledge of the object's appearance. Prior work in online static/dynamic segmentation [1] is extended to identify multiple instances of dynamic objects by introducing an unsupervised motion clustering step. These clusters are then used to update a multi-class classifier within a self-supervised framework. In contrast to many tracking-by-detection based methods, our system is able to detect dynamic objects without any prior knowledge of their visual appearance shape or location. Furthermore, the classifier is used to propagate labels of the same object in previous frames, which facilitates the continuous tracking of individual objects based on motion. The proposed system is evaluated using recall and false alarm metrics in addition to a new multi-instance labelled dataset to measure the performance of segmenting multiple instances of objects.

Authors

• Alex Bewley
• Vitor Guizilini
• Fabio Ramos 0001
• Ben Upcroft

Keywords

• Dynamics
• Optical imaging
• Training
• Motion segmentation
• Cameras
• Feature extraction
• Object recognition
• Dynamic Objects
• Multi-label
• Object Tracking
• Previous Frame
• Object Appearance
• Object Instances
• Receiver Operating Characteristic Curve
• Binary Classification
• Pedestrian
• Class Labels
• Single Cluster
• Multiple Objects
• Optical Flow
• Training Examples
• Decision Boundary
• Current Frame
• Objects In The Scene
• Density Imaging
• Random Sample Consensus
• Dynamic Clustering
• Examples Of Objects
• Dynamic Point
• Camera Motion
• Temporal Consistency
• Fundamental Matrix
• KITTI Dataset
• Unsupervised Framework
• Static Background
• True Class