Track Everything: Limiting Prior Knowledge in Online Multi-Object Recognition
This work addresses the problem of robust, general-purpose object recognition in video sequences for applications like surveillance or robotics, though it is incremental by building on existing tracking and classification methods.
The paper tackles online multi-object tracking and classification by first tracking all objects without object-specific prior knowledge, then classifying them with a fast-learning shallow CNN, showing that recognition improves when combined with tracking state information, achieving competitive performance on the Neovision2 Tower benchmark.
This paper addresses the problem of online tracking and classification of multiple objects in an image sequence. Our proposed solution is to first track all objects in the scene without relying on object-specific prior knowledge, which in other systems can take the form of hand-crafted features or user-based track initialization. We then classify the tracked objects with a fast-learning image classifier that is based on a shallow convolutional neural network architecture and demonstrate that object recognition improves when this is combined with object state information from the tracking algorithm. We argue that by transferring the use of prior knowledge from the detection and tracking stages to the classification stage we can design a robust, general purpose object recognition system with the ability to detect and track a variety of object types. We describe our biologically inspired implementation, which adaptively learns the shape and motion of tracked objects, and apply it to the Neovision2 Tower benchmark data set, which contains multiple object types. An experimental evaluation demonstrates that our approach is competitive with state-of-the-art video object recognition systems that do make use of object-specific prior knowledge in detection and tracking, while providing additional practical advantages by virtue of its generality.