Robust Tracking via Weighted Online Extreme Learning Machine

TL;DR

This paper introduces a robust online tracking method based on an improved extreme learning machine that adaptively balances classification, learns incrementally, and uses a forgetting factor to handle dynamic changes, outperforming existing methods.

Contribution

The paper proposes a novel weighted online ELM with local weight matrix, incremental learning, and a sample optimization strategy to enhance tracking robustness and accuracy.

Findings

Outperforms state-of-the-art methods in various challenging scenarios.

Effectively handles occlusion, illumination changes, and deformation.

Achieves higher robustness and accuracy in 20 benchmark sequences.

Abstract

The tracking method based on the extreme learning machine (ELM) is efficient and effective. ELM randomly generates input weights and biases in the hidden layer, and then calculates and computes the output weights by reducing the iterative solution to the problem of linear equations. Therefore, ELM offers the satisfying classification performance and fast training time than other discriminative models in tracking. However, the original ELM method often suffers from the problem of the imbalanced classification distribution, which is caused by few target objects, leading to under-fitting and more background samples leading to over-fitting. Worse still, it reduces the robustness of tracking under special conditions including occlusion, illumination, etc. To address above problems, in this paper, we present a robust tracking algorithm. First, we introduce the local weight matrix that is the dynamic creation from the data distribution at the current frame in the original ELM so as to balance between the empirical and structure risk, and fully learn the target object to enhance the classification performance. Second, we improve it to the incremental learning method ensuring tracking real-time and efficient. Finally, the forgetting factor is used to strengthen the robustness for changing of the classification distribution with time. Meanwhile, we propose a novel optimized method to obtain the optimal sample as the target object, which avoids tracking drift resulting from noisy samples. Therefore, our tracking method can fully learn both of the target object and background information to enhance the tracking performance, and it is evaluated in 20 challenge image sequences with different attributes including illumination, occlusion, deformation, etc., which achieves better performance than several state-of-the-art methods in terms of effectiveness and robustness.