• 한국멀티미디어학회논문지
• /
• 제19권10호
• /
• pp.1782-1791
• /
• 2016

Various color spaces such as RGB, HSV, log-chromaticity have been used in the field of person re-identification. However, not enough studies have been done to find suitable color space for the re-identification. This paper reviews color invariance of color spaces by diagonal model and explores the suitability of each color space in the application of person re-identification. It also proposes a method for person re-identification based on a histogram refinement technique and some fusion strategies of color spaces. Two public datasets (ALOI and ImageLab) were used for the suitability test on color space and the ImageLab dataset was used for evaluating the feasibility of the proposed method for person re-identification. Experimental results show that RGB and HSV are more suitable for the re-identification problem than other color spaces such as normalized RGB and log-chromaticity. The cumulative recognition rates up to the third rank under RGB and HSV were 79.3% and 83.6% respectively. Furthermore, the fusion strategy using max score showed performance improvement of 16% or more. These results show that the proposed method is more effective than some other methods that use single color space in person re-identification.

• Journal of Information Processing Systems
• /
• 제15권4호
• /
• pp.785-796
• /
• 2019

Due to the view point, illumination, personal gait and other background situation, person re-identification across cameras has been a challenging task in video surveillance area. In order to address the problem, a novel method called Joint Bayesian across different cameras for person re-identification (JBR) is proposed. Motivated by the superior measurement ability of Joint Bayesian, a set of Joint Bayesian matrices is obtained by learning with different camera pairs. With the global Joint Bayesian matrix, the proposed method combines the characteristics of multi-camera shooting and person re-identification. Then this method can improve the calculation precision of the similarity between two individuals by learning the transition between two cameras. For investigating the proposed method, it is implemented on two compare large-scale re-ID datasets, the Market-1501 and DukeMTMC-reID. The RANK-1 accuracy significantly increases about 3% and 4%, and the maximum a posterior (MAP) improves about 1% and 4%, respectively.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.891-902
• /
• 2020

The Re-Identification(Re-ID) is one of the most popular researches in the field of computer vision due to a variety of applications. To achieve a high-level re-identification performance, recently other methods have developed the deep learning based networks that are specialized for only person or vehicle. However, most of the current methods are difficult to be used in real-world applications that require re-identification of both person and vehicle at the same time. To overcome this limitation, this paper proposes a deep neural network learning method that combines triplet and softmax loss to improve performance and re-identify people and vehicles simultaneously. It's possible to learn the detailed difference between the identities(IDs) by combining the softmax loss with the triplet loss. In addition, weights are devised to avoid bias in one-side loss when combining. We used Market-1501 and DukeMTMC-reID datasets, which are frequently used to evaluate person re-identification experiments. Moreover, the vehicle re-identification experiment was evaluated by using VeRi-776 and VehicleID datasets. Since the proposed method does not designed for a neural network specialized for a specific object, it can re-identify simultaneously both person and vehicle. To demonstrate this, an experiment was performed by using a person and vehicle re-identification dataset together.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권4호
• /
• pp.2075-2092
• /
• 2017

Person re-identification is to match pedestrians observed from non-overlapping camera views. It has important applications in video surveillance such as person retrieval, person tracking, and activity analysis. However, it is a very challenging problem due to illumination, pose and viewpoint variations between non-overlapping camera views. In this work, we propose a viewpoint invariant method for matching pedestrian images using orientation of pedestrian. First, the proposed method divides a pedestrian image into patches and assigns angle to a patch using the orientation of the pedestrian under the assumption that a person body has the cylindrical shape. The difference between angles are then used to compute the similarity between patches. We applied the proposed method to real-time global multi-object tracking across multiple disjoint cameras with non-overlapping field of views. Re-identification algorithm makes global trajectories by connecting local trajectories obtained by different local trackers. The effectiveness of the viewpoint invariant method for person re-identification was validated on the VIPeR dataset. In addition, we demonstrated the effectiveness of the proposed approach for the inter-camera multiple object tracking on the MCT dataset with ground truth data for local tracking.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권2호
• /
• pp.775-792
• /
• 2015

Person re-identification is an important and challenging task in computer vision with numerous real world applications. Despite significant progress has been made in the past few years, person re-identification remains an unsolved problem. This paper presents a novel appearance-based approach to person re-identification. The approach exploits region covariance matrix and color histograms to capture the statistical properties and chromatic information of each object. Robustness against low resolution, viewpoint changes and pose variations is achieved by a novel signature, that is, the combination of Log Covariance Matrix feature and HSV histogram (LCMH). In order to further improve re-identification performance, third-party image sets are utilized as a common reference to sufficiently represent any image set with the same type. Distinctive and reliable features for a given image set are extracted through decision boundary between the specific set and a third-party image set supervised by max-margin criteria. This method enables the usage of an existing dataset to represent new image data without time-consuming data collection and annotation. Comparisons with state-of-the-art methods carried out on benchmark datasets demonstrate promising performance of our method.

• IEIE Transactions on Smart Processing and Computing
• /
• 제6권3호
• /
• pp.193-199
• /
• 2017

Instead of using only spatial features from a single frame for person re-identification, a combination of spatial and temporal factors boosts the performance of the system. A recurrent neural network (RNN) shows its effectiveness in generating highly discriminative sequence-level human representations. In this work, we implement RNN, three Long Short Term Memory (LSTM) network variants, and Gated Recurrent Unit (GRU) on Caffe deep learning framework, and we then conduct experiments to compare performance in terms of size and accuracy for person re-identification. We propose using GRU for the optimized choice as the experimental results show that the GRU achieves the highest accuracy despite having fewer parameters than the others.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.472-474
• /
• 2019

Because of the difference in network structure and loss function, Verification and identification models have their respective advantages and limitations for person reidentification (re-ID). In this work, we propose a multi-task network simultaneously computes the identification loss and verification loss for person reidentification. Given a pair of images as network input, the multi-task network simultaneously outputs the identities of the two images and whether the images belong to the same identity. In experiments, we analyze the major factors affect the accuracy of person reidentification. To address the occlusion problem and improve the generalization ability of reID models, we use the Random Erasing Augmentation (REA) method to preprocess the images. The method can be easily applied to different pre-trained networks, such as ResNet and VGG. The experimental results on the Market1501 datasets show significant and consistent improvements over the state-of-the-art methods.

• IEIE Transactions on Smart Processing and Computing
• /
• 제6권4호
• /
• pp.262-268
• /
• 2017

Intelligent video surveillance systems have been developed to monitor global areas and find specific target objects using a large-scale database. However, person re-identification presents some challenges, such as pose change and occlusions. To solve the problems, this paper presents an improved person re-identification method using sparse representation and saliency-based dictionary construction. The proposed method consists of three parts: i) feature description based on salient colors and textures for dictionary elements, ii) orthogonal atom selection using cosine similarity to deal with pose and viewpoint change, and iii) measurement of reconstruction error to rank the gallery corresponding a probe object. The proposed method provides good performance, since robust descriptors used as a dictionary atom are generated by weighting some salient features, and dictionary atoms are selected by reducing excessive redundancy causing low accuracy. Therefore, the proposed method can be applied in a large scale-database surveillance system to search for a specific object.

• 전기전자학회논문지
• /
• 제23권4호
• /
• pp.1166-1174
• /
• 2019

이 논문에서는 사람 재식별 모델인 PersonNet의 성능을 개선하는 방법을 제안하고 실험한다. 특징점 추출을 위해 인셉션 레이어를 접목하여, 기존 32개의 특징점을 154개로 증가시켜 강화하였다. 또한, PersonNet에서 사용하는 CND 방식을 수정하여 비대칭성을 완화하였고, 보행자 이미지의 특징점을 3부분으로 나누어 가중치를 적용한 방법을 적용하여 특징을 더 뚜렷하게 파악하도록 하였다. 성능 평가를 위해 CUHK01, CUHK03 그리고 Market-1501 3가지의 데이터베이스를 사용하였고 실험 결과 27~31% 성능이 개선되었다.

• 한국인터넷방송통신학회논문지
• /
• 제17권2호
• /
• pp.15-23
• /
• 2017

사람의 빈번한 자세 변화, 그리고 background clutter과 occlusion으로 인해 Person Re-identificatio는 컴퓨터 비전 분야에서 가장 어려운 부분이다. 비겹침 카메라의 이미지는 어떤 사람을 다른 사람과 구별하기 어렵게 한다. 더욱 나은 성능 일치를 달성하기 위해 대부분의 방법은 특징 선택과 거리 메트릭을 개별적으로 사용한다. 그렇게 차별화된 표현과 적절한 거리를 얻을 수 있고, 사람과 중요한 특징의 무시 사이의 유사성을 설명할 수 있다. 이러한 상황은 우리가 이 문제를 다루는 새로운 방법을 고려하도록 한다. 본 논문에서는 Person Re-identification를 위한 3단 계층네트워크를 갖는 향상되고 반복적인 신경 회로망을 제안하였다. 특히 RNN(Revurrent Neural Network) 모델은 반복적인 EM(Expectation Maximum) 알고리즘과 3단 계층 네트워크를 포함하고, 차별적 특징과 지표 거리를 공동으로 학습한다. 반복적인 EM 알고리즘은 RNN 이전에 연속해 있는 CNN(Convoutional Neural Network)의 특징 추출 능력을 충분히 사용할 수 있다. 자율 학습을 통해 EM 프레임 워크는 패치의 레이블을 변경하고 더 큰 데이터 세트를 훈련할 수 있다. 네트워크를 더 잘 훈련시키기 위해 3단 계층 네트워크를 통해 CNN, RNN 및 풀링 계층이 공동으로 특징 추출을 할 수 있다. 실험 결과에 따르면 비전처리 분야에서 다른 연구자의 접근 방식과 비교할 때 이 방법은 경쟁력 있는 정확도를 얻을 수 있다. 이 방법에 대한 다른 요소의 영향은 향후 연구에서 분석되고 평가될 것이다.