Person Recognition System Based on a Combination of Body Images from Visible Light and Thermal Cameras

By Tien Dat Nguyen, Hyung Gil Hong, Ki-Wan Kim, Kang Ryoung Park. Italian National Conference on Sensors, 2017

723 citations recorded by the source corpus.

The human body contains identity information that can be used for the person recognition (verification/recognition) problem. In this paper, we propose a person recognition method using the information extracted from body images. Our research is novel in the following three ways compared to previous studies. First, we use the images of human body for recognizing individuals. To overcome the limitations of previous studies on body-based person recognition that use only visible light images for recognition, we use human body images captured by two different kinds of camera, including a visible light camera and a thermal camera. The use of two different kinds of body image helps us to reduce the effects of noise, background, and variation in the appearance of a human body. Second, we apply a state-of-the art method, called convolutional neural network (CNN) among various available methods, for image features extraction in order to overcome the limitations of traditional hand-designed image feature extraction methods. Finally, with the extracted image features from body images, the recognition task is performed by measuring the distance between the input and enrolled samples. The experimental results show that the proposed method is efficient for enhancing recognition accuracy compared to systems that use only visible light or thermal images of the human body.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/6c518aabdbba2c073eab6a3bb4120023851e524c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Deep Multimodal Data Fusion (2024, neutral): “…Face Anti Proofing RGB + Thermal CASIA-SURF [230], CASIA-SURF Cefa [102] Speakingfaces [1], ThermalFace [8], TTVF [63], UL-FMTV [52], Person Re-Identification RGB+Thermal RegDB [131], SYSU-MM01 [196], BIWI RGBD-ID [127], RGBD-ID [13], SUCVL RGBD-ID [120], RobotPKU [105], KinectREID [135] task.”
Deep Learning for Person Re-Identification: A Survey and Outlook (2020, background): “However, in practical open-world applications, the data might be heterogeneous, e.g ., the person images are captured by cameras with different light spectrums [20], [51], sketches [52] or depth images [53], and even text descriptions [54].”
Hierarchical Discriminative Learning for Visible Thermal Person Re-Identification (2018, methodology): “Note that our setting is totally different from that in (Nguyen et al. 2017), since we focus on cross-modal re-identification.”
Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification (2020, background): “Following (Ye et al. 2018a; 2018b), the results of RegDB are based on the average of 10 times repeated random split of training and testing sets.”
Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification (2020, methodology): “Cross-modality visible-infrared person re-identification (VI-ReID) [50,58] aims to solve this problem by matching images of people captured by visible and infrared (including near- [50] and far-infrared (thermal) [29]) cameras.”
Channel Augmented Joint Learning for Visible-Infrared Recognition (2021, methodology): “RegDB [26] dataset is captured by one visible and one far-infrared (thermal) camera.”
Infrared-Visible Cross-Modal Person Re-Identification with an X Modality (2020, methodology): “%) with the state-of-the-art IV-ReID methods on RegDB and SYSU-MM01 datasets.”
Bi-Directional Center-Constrained Top-Ranking for Visible Thermal Person Re-Identification (2020, methodology): “Example images from (a) RegDB [36] and (b) SYSU-MM01 [11] datasets.”
Cross-Modality Person Re-Identification With Shared-Specific Feature Transfer (2020, background): “RegDB is collected by dual camera systems [31].”
Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification (2019, methodology): “We followed the RegDB evaluation protocol in [37, 39] and the SYSU-MM01 evaluation protocol Datasets RegDB [21] SYSU-MM01 [33] Methods R=1 R=10 mAP R=1 R=10 mAP”