• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.2094-2112
• /
• 2019

Focusing on the issue that the conventional Kernel Correlation Filter (KCF) algorithm has poor performance in handling scale change and obscured objects, this paper proposes an anti-occlusion and scale adaptive tracking algorithm in the basis of KCF. The average Peak-to Correlation Energy and the peak value of correlation filtering response are used as the confidence indexes to determine whether the target is obscured. In the case of non-occlusion, we modify the searching scheme of the KCF. Instead of searching for a target with a fixed sample size, we search for the target area with multiple scales and then resize it into the sample size to compare with the learnt model. The scale factor with the maximum filter response is the best target scaling and is updated as the optimal scale for the following tracking. Once occlusion is detected, the model updating and scale updating are stopped. Experiments have been conducted on the OTB benchmark video sequences for compassion with other state-of-the-art tracking methods. The results demonstrate the proposed method can effectively improve the tracking success rate and the accuracy in the cases of scale change and occlusion, and meanwhile ensure a real-time performance.

• 한국멀티미디어학회논문지
• /
• 제20권2호
• /
• pp.126-133
• /
• 2017

The conventional hand-crafted features used to track objects have limitations in object representation. Convolutional neural networks, which show good performance results in various areas of computer vision, are emerging as new ways to break through the limitations of feature extraction. CNN extracts the features of the image through layers of multiple layers, and learns the kernel used for feature extraction by itself. In this paper, we use the feature map extracted from the convolution layer of the convolution neural network to create an outline model of the object and use it for tracking. We propose a method to adaptively update the outline model to cope with various environment change factors affecting the tracking performance. The proposed algorithm evaluated the validity test based on the 11 environmental change attributes of the CVPR2013 tracking benchmark and showed excellent results in six attributes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권9호
• /
• pp.4438-4460
• /
• 2017

The Kernelized Correlation Filters (KCF) tracker has caused the extensive concern in recent years because of the high efficiency. Numerous improvements have been made successively. However, due to the abrupt motion between the consecutive image frames, these methods cannot track object well. To cope with the problem, we propose an extended KCF tracker based on swarm intelligence method. Unlike existing KCF-based trackers, we firstly introduce a swarm-based sampling method to KCF tracker and design a unified framework to track smooth or abrupt motion simultaneously. Secondly, we propose a global motion estimation method, where the exploration factor is constructed to search the whole state space so as to adapt abrupt motion. Finally, we give an adaptive threshold in light of confidence map, which ensures the accuracy of the motion estimation strategy. Extensive experimental results in both quantitative and qualitative measures demonstrate the effectiveness of our proposed method in tracking abrupt motion.

• 한국정보처리학회논문지
• /
• 제4권10호
• /
• pp.2461-2469
• /
• 1997

목표물 탐지 및 인식은 신경망의 적용이 활발한 하나의 분야로서, 일반적인 형태인식 문제들의 요구 사항에 추가적으로 translation invariance와 실시간 처리를 요구한다. 본 논문에서는 이러한 요구 사항을 만족하는 새로운 신경망의 구조를 소개하고, 이의 효과적인 학습 방법을 설명한다. 제안된 신경망은 특징 추출 단계와 형태 인식 단계가 연속(Cascade)된 가중치 공유 신경망(Shared-weight Neural Network)을 기본으로하여 이를 확장한 형태이다. 이 신경망의 특징 추출 단계는 입력에 가중치 창(weight kernel)으로 코릴레이션 형태의 연산을 수행하며, 신경망 전체를 하나의 2차원 비선형 코릴레이션 필터로 볼 수 있다. 따라서, 신경망의 최종 출력은 목표물 위치에 첨예(peak)값을 갖는 코릴레이션 평면이다. 이 신경망이 갖는 구조는 병렬 또는 분산 처리 컴퓨터로의 구현에 매우 적합하며, 이러한 사실은 실시간 처리가 중요한 요인이 되는 문제에 적용할 수 있음을 의미한다. 목표물과 비목표물간의 숫자상 불균형으로 인하여 초래되는 오경보(false alarm) 발생의 문제를 극복하기 위한 새로운 학습 방법도 소개한다. 성능 검증을 위하여 제안된 신경망을 주차장내에서 이동하는 특정 차량의 탐지 및 인식 문제에 적용하였다. 그 결과 오경보 발생이 없었으며, 중형급 컴퓨터를 이용하여 약 190Km로 이동하는 차량의 추적이 가능한 정도의 빠른 처리 결과를 보여 주었다.