Active Mining of Parallel Video Streams
This work addresses practical limitations in video surveillance systems by enabling robust track classification in evolving multi-camera scenarios, though it appears incremental as it builds on existing semi-supervised and ensemble methods.
The paper tackles the problem of reducing human burden in video surveillance by proposing a semi-supervised incremental learning framework for evolving visual streams, achieving high accuracy with minimal human collaboration in experiments on synthetic and real-world data.
The practicality of a video surveillance system is adversely limited by the amount of queries that can be placed on human resources and their vigilance in response. To transcend this limitation, a major effort under way is to include software that (fully or at least semi) automatically mines video footage, reducing the burden imposed to the system. Herein, we propose a semi-supervised incremental learning framework for evolving visual streams in order to develop a robust and flexible track classification system. Our proposed method learns from consecutive batches by updating an ensemble in each time. It tries to strike a balance between performance of the system and amount of data which needs to be labelled. As no restriction is considered, the system can address many practical problems in an evolving multi-camera scenario, such as concept drift, class evolution and various length of video streams which have not been addressed before. Experiments were performed on synthetic as well as real-world visual data in non-stationary environments, showing high accuracy with fairly little human collaboration.