CoChat

Convolutional Neural Network-Based Human Detection in Nighttime Images Using Visible Light Camera Sensors

Open access
Kim, Jong, Hong, Hyung, Park, Kang · 2017 · Sensors

The DOI matches its Crossref record; 54 of the 56 references it cites were found in a registry or an index.

Abstract

Because intelligent surveillance systems have recently undergone rapid growth, research on accurately detecting humans in videos captured at a long distance is growing in importance. The existing research using visible light cameras has mainly focused on methods of human detection for daytime hours when there is outside light, but human detection during nighttime hours when there is no outside light is difficult. Thus, methods that employ additional near-infrared (NIR) illuminators and NIR cameras or thermal cameras have been used. However, in the case of NIR illuminators, there are limitations in terms of the illumination angle and distance. There are also difficulties because the illuminator power must be adaptively adjusted depending on whether the object is close or far away. In the case of thermal cameras, their cost is still high, which makes it difficult to install and use them in a variety of places. Because of this, research has been conducted on nighttime human detection using visible light cameras, but this has focused on objects at a short distance in an indoor environment or the use of video-based methods to capture multiple images and process them, which causes problems related to the increase in the processing time. To resolve these problems, this paper presents a method that uses a single image captured at night on a visible light camera to detect humans in a variety of environments based on a convolutional neural network. Experimental results using a self-constructed Dongguk night-time human detection database (DNHD-DB1) and two open databases (Korea advanced institute of science and technology (KAIST) and computer vision center (CVC) databases), as well as high-accuracy human detection in a variety of environments, show that the method has excellent performance compared to existing methods.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/s17051065

Cites

54 of 54 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Flowchart of proposed method.
Figure 1 Flowchart of proposed method.CC BY · PubMed Central
Figure 2 Proposed CNN architecture.
Figure 2 Proposed CNN architecture.CC BY · PubMed Central
Figure 3 Examples from three databases used in experiments: (a) collected images of DNHD-DB1; (b) human and background images of DNHD-DB1; (c) collected image of KAIST database; (d) human and background images of KAIST database; (e) collected image of CVC-14 database; and (f) human and background images of CVC-14 database. In (a,c,e), human areas are shown as red dashed box. In (b,d,f), left three figures are human images whereas the right three ones are background images, respectively.
Figure 3 Examples from three databases used in experiments: (a) collected images of DNHD-DB1; (b) human and background images of DNHD-DB1; (c) collected image of KAIST database; (d) human and background images of KAIST database; (e) collected image of CVC-14 database; and (f) human and background images of CVC-14 database. In (a,c,e), human areas are shown as red dashed box. In (b,d,f), left three figures are human images whereas the right three ones are background images, respectively.CC BY · PubMed Central
Figure 4 Examples of loss and accuracy curves with training data of four-fold cross validation in case of using combined database images: (a) 1st fold; (b) 2nd fold; (c) 3rd fold; and (d) 4th fold.
Figure 4 Examples of loss and accuracy curves with training data of four-fold cross validation in case of using combined database images: (a) 1st fold; (b) 2nd fold; (c) 3rd fold; and (d) 4th fold.CC BY · PubMed Central
Figure 5 Examples of 96 filters obtained from 1st convolution layer through training: (a) CVC-14 database; (b) DNHD-DB1; (c) KAIST database; and (d) combined database. In (a–d), the left four images show the 96 filters obtained by training with the original images, whereas the right four images represent those obtained by training with the HE images. In the left and right four images, the left-upper, right-upper, left-lower, and right lower images show the 96 filters obtained by training using 1-, 2-, 3-, and 4-fold cross validation, respectively.
Figure 5 Examples of 96 filters obtained from 1st convolution layer through training: (a) CVC-14 database; (b) DNHD-DB1; (c) KAIST database; and (d) combined database. In (a–d), the left four images show the 96 filters obtained by training with the original images, whereas the right four images represent those obtained by training with the HE images. In the left and right four images, the left-upper, right-upper, left-lower, and right lower images show the 96 filters obtained by training using 1-, 2-, 3-, and 4-fold cross validation, respectively.CC BY · PubMed Central
Figure 6 ROC curves of human and background detection: (a) with original images, ROC curves in the part ranges of FPR and TPR (top), ROC curves in the whole ranges of FPR and TPR (bottom) and (b) with HE processed images, ROC curves in the part ranges of FPR and TPR (top), ROC curves in the whole ranges of FPR and TPR (bottom).
Figure 6 ROC curves of human and background detection: (a) with original images, ROC curves in the part ranges of FPR and TPR (top), ROC curves in the whole ranges of FPR and TPR (bottom) and (b) with HE processed images, ROC curves in the part ranges of FPR and TPR (top), ROC curves in the whole ranges of FPR and TPR (bottom).CC BY · PubMed Central
Figure 7 Examples of FN and FP errors in cases using original images of (a) CVC-14 database; (b) DNHD-DB1; and (c) KAIST database. In (a–c), the left two images show the FN cases, whereas the right two images represent the FP cases.
Figure 7 Examples of FN and FP errors in cases using original images of (a) CVC-14 database; (b) DNHD-DB1; and (c) KAIST database. In (a–c), the left two images show the FN cases, whereas the right two images represent the FP cases.CC BY · PubMed Central
Figure 8 Examples of FN and FP errors in cases using HE processed images of (a) CVC-14 database; (b) DNHD-DB1; and (c) KAIST database. In (a–c), the left two images show the FN cases, whereas the right two images represent the FP cases.
Figure 8 Examples of FN and FP errors in cases using HE processed images of (a) CVC-14 database; (b) DNHD-DB1; and (c) KAIST database. In (a–c), the left two images show the FN cases, whereas the right two images represent the FP cases.CC BY · PubMed Central
Figure 9 ROC curves of human and background detection by proposed and previous methods [16,42]. ROC curves in the part ranges of FPR and TPR (top), ROC curves in the whole ranges of FPR and TPR (bottom).
Figure 9 ROC curves of human and background detection by proposed and previous methods [16,42]. ROC curves in the part ranges of FPR and TPR (top), ROC curves in the whole ranges of FPR and TPR (bottom).CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 2

  1. Oren, M., Papageorgiou, C., Sinha, P., Osuna, E., and Poggio, T. (1997, January 17–19). Pedestrian detection using wavelet templates. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Juan, Puerto Rico.
  2. Gonzalez, R.C., and Woods, R.E. (2010). Digital Image Processing, Prentice Hall. [3rd ed.].

Cited by

See all 94

Metadata

Authors
Kim, J., Hong, H., & Park, K.
Affiliations
Dongguk University (KR)
Corresponding author
Park, Kang
Venue
Sensors
Publisher
MDPI AG
Published
2017-05-08
Volume
17
Issue
5
Pages
1065
ISSN
1424-8220 (ISSN-L)
OpenAlex
W2613296094
Cited by
78
References
56
Citations by year
2026: 5 · 2025: 5 · 2024: 6 · 2023: 3 · 2022: 5 · 2021: 16 · 2020: 9 · 2019: 15 · 2018: 10 · 2017: 4
FWCI
4.31
Type
journal article
Language
en
Open access
Locations
  • Sensors (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
Keywords
visible camera, convolutional neural networks, intelligent surveillance

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.