Object detection and tracking benchmark in industry based on improved correlation filter

TL;DR

This paper introduces Dijkstra-distance based correlation filters (DBCF) for improved object detection and tracking in industrial settings, addressing data diversity challenges with a new learning framework and benchmark dataset.

Contribution

It proposes a novel DBCF method that incorporates distribution constraints via shortest path optimization, enhancing performance on industrial data.

Findings

DBCF outperforms existing methods in industrial scenarios.

The new dataset provides a valuable benchmark for industrial object detection.

Extensive experiments validate the effectiveness of DBCF.

Abstract

Real-time object detection and tracking have shown to be the basis of intelligent production for industrial 4.0 applications. It is a challenging task because of various distorted data in complex industrial setting. The correlation filter (CF) has been used to trade off the low-cost computation and high performance. However, traditional CF training strategy can not get satisfied performance for the various industrial data; because the simple sampling(bagging) during training process will not find the exact solutions in a data space with a large diversity. In this paper, we propose Dijkstra-distance based correlation filters (DBCF), which establishes a new learning framework that embeds distribution-related constraints into the multi-channel correlation filters (MCCF). DBCF is able to handle the huge variations existing in the industrial data by improving those constraints based on the shortest path among all solutions. To evaluate DBCF, we build a new dataset as the benchmark for industrial 4.0 application. Extensive experiments demonstrate that DBCF produces high performance and exceeds the state-of-the-art methods. The dataset and source code can be found at https://github.com/bczhangbczhang