2021
DOI: 10.5815/ijigsp.2021.01.04
|View full text |Cite
|
Sign up to set email alerts
|

Pedestrian Detection in Thermal Images Using Deep Saliency Map and Instance Segmentation

Abstract: Pedestrian detection is an established instance of computer vision task. Pedestrian detection from the color images has achieved robust performance but in the night time or in bad light conditions it has low detection accuracy. Thermal images are used for detecting people at night time, foggy weather or in bad lighting situations when color images have a lower vision. But in the daytime where the surroundings are warm or warmer than pedestrians then the thermal image has lower accuracy. Hence thermal and color… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3

Citation Types

0
3
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
3
3
2

Relationship

0
8

Authors

Journals

citations
Cited by 9 publications
(3 citation statements)
references
References 38 publications
0
3
0
Order By: Relevance
“…Image recognition technology, especially the application of image recognition technology based on deep learning, provides necessary support for accurate recognition and efficient processing of financial original vouchers. At present, among the deep learning algorithms, the text recognition algorithms include fast RCNN, mask RCNN [7], YOLOs [8], Textboxes [9], Graph Convolutional Network [10], and the character recognition algorithms include CRNN [11][12], RARE [13], and FOTS [14]. These algorithms are implemented by training on a large amount of sample data, and deep learning models are able to learn the features and patterns of different types of vouchers to accurately match vouchers in a graph with known vouchers.…”
Section: Introductionmentioning
confidence: 99%
“…Image recognition technology, especially the application of image recognition technology based on deep learning, provides necessary support for accurate recognition and efficient processing of financial original vouchers. At present, among the deep learning algorithms, the text recognition algorithms include fast RCNN, mask RCNN [7], YOLOs [8], Textboxes [9], Graph Convolutional Network [10], and the character recognition algorithms include CRNN [11][12], RARE [13], and FOTS [14]. These algorithms are implemented by training on a large amount of sample data, and deep learning models are able to learn the features and patterns of different types of vouchers to accurately match vouchers in a graph with known vouchers.…”
Section: Introductionmentioning
confidence: 99%
“…Mask RCNN combines object detection and image segmentation, which results in the creation of a bounding box around the detected object and a mask on the portion of the image that belongs to the said object 21 . Many researchers are using mask RCNN for a variety of applications starting from fruit detection for robot-augmented harvesting 19 to human detection for surveillance purposes 22 . Mask RCNN has also been used for cell detection for breast cancer applications using IR images 23 .…”
Section: Introductionmentioning
confidence: 99%
“…However, the suitability of a saliency network for augmentation is not properly analysed in [3]. In [21], a network is proposed which introduces instance-level segmentation in pedestrian detection using thermal images. Authors in [22] proposes a two-stage method for improving detection in pedestrian.…”
Section: Introductionmentioning
confidence: 99%