Fast Task-Specific Target Detection via Graph Based Constraints Representation and Checking
This work addresses efficient task-specific object detection for robotics applications, presenting an incremental improvement with a bounded time guarantee.
The paper tackles the problem of fast target detection for robotics by proposing an early recognition concept and a sub-optimal checking order policy, achieving bounded time cost compared to the optimal sequence and validating the approach on rigid object and non-rigid body part detection scenarios.
In this work, we present a fast target detection framework for real-world robotics applications. Considering that an intelligent agent attends to a task-specific object target during execution, our goal is to detect the object efficiently. We propose the concept of early recognition, which influences the candidate proposal process to achieve fast and reliable detection performance. To check the target constraints efficiently, we put forward a novel policy to generate a sub-optimal checking order, and prove that it has bounded time cost compared to the optimal checking sequence, which is not achievable in polynomial time. Experiments on two different scenarios: 1) rigid object and 2) non-rigid body part detection validate our pipeline. To show that our method is widely applicable, we further present a human-robot interaction system based on our non-rigid body part detection.