Comparative Study of Various Feature Extraction Techniques for Pedestrian Detection

Hiranmai, M; B, Niranjana Krupa; Nagaraj, H K

doi:10.1016/j.procs.2019.06.098

Cited by 8 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was shown that the suggested OCD technique is quite good at identifying pedestrian outlines. HOG-XCSLBP features with a LSVM classi er [17] outperformed HOG-LBP. Additionally, it was shown that HOG-XCSLBP had a lower false alarm rate and improved pedestrian recognition.…”

Section: Feature Extraction Techniques For Pedestrian Detectionmentioning

confidence: 98%

“…The effectiveness of HOG and its variations was compared to that of LBP and its modi cations, including CSLBP and the local ternary pattern (LTP), in the detection of pedestrians. The SIFT-inspired SURF descriptor [17,20] was used to implement object detection. The technique performed better in terms of image variety, robustness, and uniqueness.…”

Section: Feature Extraction Techniques For Pedestrian Detectionmentioning

confidence: 99%

“…Utilizing SVM as a classi er, experimental evaluations of the OCD ,SURF, HOG, and SIFT feature extraction techniques [17,21] were conducted. It was shown that the suggested OCD technique is quite good at identifying pedestrian outlines.…”

Section: Feature Extraction Techniques For Pedestrian Detectionmentioning

confidence: 99%

“…On the MIT pedestrian dataset[16], the HOG feature extraction approach was combined with the linear support vector machine (SVM) [17,18] to get almost awless results. Additionally, a separate dataset called "INRIA," which consists of human images with various backdrops and poses was used to demonstrate that HOG performs better.…”

Section: Feature Extraction Techniques For Pedestrian Detectionmentioning

confidence: 99%

See 3 more Smart Citations

An Improved Parallel Feature Fusion - CBAM method for occluded pedestrian identification

Shaamili

Bevi

2023

Preprint

View full text Add to dashboard Cite

Occluded pedestrian identification is a critical and challenging issue in the field of pedestrian detection. Currently, using pedestrian components or human approaches is the most popular way to get over the problem of occlusion in pedestrian recognition. Only a small portion of the body may be used for detection when there is severe occlusion from crowds, or human or pedestrian components. The viewable portions of the occluded pedestrian have a small scale, but the scales of the unobscured and occluded pedestrians in the same image are different. Improved Parallel Feature Fusion with CBAM (IPFF-CBAM) on Feature Pyramid Network is put forward that can integrate new feature data of various sizes which are applied to four benchmark datasets KITTI, WiderPerson, CrowdHuman, and INRIA individuals of occluded pedestrians, in order to enhance key attributes. According to the findings the proposed method performs satisfactorily on deep learning approaches i.e., Faster RCNN, Cascade RCNN and Mask RCNN to obtain results of parameters like Average Precision (AP) and Miss rate index (MR) in obstructed pedestrian detection tasks.

show abstract

Section: Feature Extraction Techniques For Pedestrian Detectionmentioning

confidence: 98%

Section: Feature Extraction Techniques For Pedestrian Detectionmentioning

confidence: 99%

Section: Feature Extraction Techniques For Pedestrian Detectionmentioning

confidence: 99%

Section: Feature Extraction Techniques For Pedestrian Detectionmentioning

confidence: 99%

See 2 more Smart Citations

An Improved Parallel Feature Fusion - CBAM method for occluded pedestrian identification

Shaamili

Bevi

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In this study, centre-symmetric local binary pattern (CS-LBP) 36 has been used for feature extraction, which was first used for matching and objects recognition. It is an effectual extension to LBP.…”

Section: Feature Extraction From the Fused Imagementioning

confidence: 99%

A multimodal architecture using Adapt‐HKFCT segmentation and feature‐based chaos integrated deep neural networks (Chaos‐DNN‐SPOA) for contactless biometricpalm vein recognition system

Rajalakshmi

Annapurani

2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

In the recent past, the fusion of various unimodal biometrics has gained increasing attention from researchers dedicated to the use of practical biometrics. In this paper, a Chaos Integrated Deep Neural Networks (Chaos-DNN) using Sandpiper Optimization Algorithm (SPOA) is proposed to enhance the perfor- | INTRODUCTIONThe biometric system is used to measure the signature points of the individual persons, such as behaviour of a person's identity. [1][2][3] Biometric systems are used for security purposes to control the data or information for future use. It is also used for internet access, securing computer systems, electronic passport control security, banking, cellular phones, credit cards, security access to buildings, health and social services, terrorist determination and corpse recognition. [4][5][6] The biometric technologies are developed using human traits, namely, DNA, ear morphology, facial characteristics, fingerprint, gait, hand geometry, finger geometry, iris, keystroke, smell, palm print, handwriting with signature, voice and so forth. Among them palm venal traits are gaining more attention and are comparatively accurate and secure. 7,8 Multimodal systems are widely used in defence to secure the data compared with the unimodal systems. The imagery of vein is caught in various portions of the hand, like, palm, palm dorsal, the wrist, finger and so forth, which are widely used in recent years of evaluation. 9,10 The vein images, like palm and dorsal part are helps to build low-cost devices. Also the image capture method is more user-friendly, less harm, rapid, lack of contact and easy to use more secure for authentication systems. Hand-based parameters are widely used because of ease to work, availability of various parameters, like, geometrical features, hand thickness, fingers, joints and RAJALAKSHMI AND ANNAPURANI PANAIYAPPAN | 1847 How to cite this article: Rajalakshmi M, Annapurani Panaiyappan K. A multimodal architecture using Adapt-HKFCT segmentation and feature-based chaos integrated deep neural networks (Chaos-DNN-SPOA) for contactless biometricpalm vein recognition system.

show abstract

A Comparative Study of Pedestrian Detection Techniques Over the Last Decade

Salam,

Jebaseeli

2024

Soft Computing: Theories and Applications

View full text Add to dashboard Cite

Comparative Study of Various Feature Extraction Techniques for Pedestrian Detection

Cited by 8 publications

References 10 publications

An Improved Parallel Feature Fusion - CBAM method for occluded pedestrian identification

An Improved Parallel Feature Fusion - CBAM method for occluded pedestrian identification

A multimodal architecture using Adapt‐HKFCT segmentation and feature‐based chaos integrated deep neural networks (Chaos‐DNN‐SPOA) for contactless biometricpalm vein recognition system

A Comparative Study of Pedestrian Detection Techniques Over the Last Decade

Contact Info

Product

Resources

About