Large-Scale Person Re-Identification Based on Deep Hash Learning
Person re-identification in the image processing domain has been a challenging research topic due to the influence of pedestrian posture, background, lighting, and other factors. In this paper, the method of harsh learning is applied in person re-identification, and we propose a person re-identifica...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-04-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/21/5/449 |
| _version_ | 1798041079894769664 |
|---|---|
| author | Xian-Qin Ma Chong-Chong Yu Xiu-Xin Chen Lan Zhou |
| author_facet | Xian-Qin Ma Chong-Chong Yu Xiu-Xin Chen Lan Zhou |
| author_sort | Xian-Qin Ma |
| collection | DOAJ |
| description | Person re-identification in the image processing domain has been a challenging research topic due to the influence of pedestrian posture, background, lighting, and other factors. In this paper, the method of harsh learning is applied in person re-identification, and we propose a person re-identification method based on deep hash learning. By improving the conventional method, the method proposed in this paper uses an easy-to-optimize shallow convolutional neural network to learn the inherent implicit relationship of the image and then extracts the deep features of the image. Then, a hash layer with three-step calculation is incorporated in the fully connected layer of the network. The hash function is learned and mapped into a hash code through the connection between the network layers. The generation of the hash code satisfies the requirements that minimize the error of the sum of quantization loss and Softmax regression cross-entropy loss, which achieve the end-to-end generation of hash code in the network. After obtaining the hash code through the network, the distance between the pedestrian image hash code to be retrieved and the pedestrian image hash code library is calculated to implement the person re-identification. Experiments conducted on multiple standard datasets show that our deep hashing network achieves the comparable performances and outperforms other hashing methods with large margins on Rank-1 and mAP value identification rates in pedestrian re-identification. Besides, our method is predominant in the efficiency of training and retrieval in contrast to other pedestrian re-identification algorithms. |
| first_indexed | 2024-04-11T22:16:28Z |
| format | Article |
| id | doaj.art-92f26390a55e439a88a1f7317708b125 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-04-11T22:16:28Z |
| publishDate | 2019-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-92f26390a55e439a88a1f7317708b1252022-12-22T04:00:22ZengMDPI AGEntropy1099-43002019-04-0121544910.3390/e21050449e21050449Large-Scale Person Re-Identification Based on Deep Hash LearningXian-Qin Ma0Chong-Chong Yu1Xiu-Xin Chen2Lan Zhou3Beijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing 100048, ChinaBeijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing 100048, ChinaBeijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing 100048, ChinaBeijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing 100048, ChinaPerson re-identification in the image processing domain has been a challenging research topic due to the influence of pedestrian posture, background, lighting, and other factors. In this paper, the method of harsh learning is applied in person re-identification, and we propose a person re-identification method based on deep hash learning. By improving the conventional method, the method proposed in this paper uses an easy-to-optimize shallow convolutional neural network to learn the inherent implicit relationship of the image and then extracts the deep features of the image. Then, a hash layer with three-step calculation is incorporated in the fully connected layer of the network. The hash function is learned and mapped into a hash code through the connection between the network layers. The generation of the hash code satisfies the requirements that minimize the error of the sum of quantization loss and Softmax regression cross-entropy loss, which achieve the end-to-end generation of hash code in the network. After obtaining the hash code through the network, the distance between the pedestrian image hash code to be retrieved and the pedestrian image hash code library is calculated to implement the person re-identification. Experiments conducted on multiple standard datasets show that our deep hashing network achieves the comparable performances and outperforms other hashing methods with large margins on Rank-1 and mAP value identification rates in pedestrian re-identification. Besides, our method is predominant in the efficiency of training and retrieval in contrast to other pedestrian re-identification algorithms.https://www.mdpi.com/1099-4300/21/5/449person re-identificationimage analysishash layerquantization lossHamming distancecross-entropy loss |
| spellingShingle | Xian-Qin Ma Chong-Chong Yu Xiu-Xin Chen Lan Zhou Large-Scale Person Re-Identification Based on Deep Hash Learning Entropy person re-identification image analysis hash layer quantization loss Hamming distance cross-entropy loss |
| title | Large-Scale Person Re-Identification Based on Deep Hash Learning |
| title_full | Large-Scale Person Re-Identification Based on Deep Hash Learning |
| title_fullStr | Large-Scale Person Re-Identification Based on Deep Hash Learning |
| title_full_unstemmed | Large-Scale Person Re-Identification Based on Deep Hash Learning |
| title_short | Large-Scale Person Re-Identification Based on Deep Hash Learning |
| title_sort | large scale person re identification based on deep hash learning |
| topic | person re-identification image analysis hash layer quantization loss Hamming distance cross-entropy loss |
| url | https://www.mdpi.com/1099-4300/21/5/449 |
| work_keys_str_mv | AT xianqinma largescalepersonreidentificationbasedondeephashlearning AT chongchongyu largescalepersonreidentificationbasedondeephashlearning AT xiuxinchen largescalepersonreidentificationbasedondeephashlearning AT lanzhou largescalepersonreidentificationbasedondeephashlearning |