國立虎尾科技大學 |

Enhancing Real-Time Vehicle and Pedestrian Detection Using YOLO With Hybrid Feature Fusion

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Enhancing Real-Time Vehicle and Pedestrian Detection Using YOLO With Hybrid Feature Fusion/ Shijon Das.
作者:	Das, Shijon,
面頁冊數:	1 electronic resource (82 pages)
附註:	Source: Masters Abstracts International, Volume: 86-11.
Contained By:	Masters Abstracts International86-11.
標題:	Robotics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32001353
ISBN:	9798315766896

Enhancing Real-Time Vehicle and Pedestrian Detection Using YOLO With Hybrid Feature Fusion
Das, Shijon,

Enhancing Real-Time Vehicle and Pedestrian Detection Using YOLO With Hybrid Feature Fusion [eletronic resource] /Shijon Das. - 1 electronic resource (82 pages)

Source: Masters Abstracts International, Volume: 86-11.

Real-time object detection is central to the development of intelligent transportation systems, autonomous vehicles, smart city monitoring, and pedestrian safety functionalities. Among several deep learning-based approaches, the You Only Look Once (YOLO) series of object detectors has been among the top choices for a long time due to the trade-off it has attained between accuracy and inference speed. This thesis gives an in-depth review and experimental analysis of YOLO versions 7-12, utilized for the use of real-time vehicle and pedestrian object detection. While earlier versions of YOLO were performance competitive, they were poor at occlusion, low-light, and detection of small objects. In order to overcome these weaknesses, this paper proposes a novel YOLOv12-hybrid feature fusion model that integrates transformer-based attention mechanisms, bidirectional multi-scale feature aggregation, and RGB, depth, and semantic segmentation cross-modal input fusion. Large-scale experiments were conducted on the COCO 2017 dataset, comparing each iteration of YOLO based on mean Average Precision (mAP), training loss convergence, and inference speed (FPS). The results establish that YOLOv12 surpasses previous models, with an mAP of 88.2% and over 47 FPS inference rates, and yet offers consistent detection in challenging urban settings. Contrast against the traditional and state-of-the-art models also indicates the dominance of YOLOv12 for real-world deployment. This work not only establishes the benchmark for YOLO detector development but also offers a scalable, accurate, and real-time enabled model structure tailored for safety-critical use cases in traffic monitoring, autonomous vehicles, and smart infrastructure systems.

English

ISBN: 9798315766896Subjects--Topical Terms:

561941
Robotics.
Subjects--Index Terms:

Deep learning

Enhancing Real-Time Vehicle and Pedestrian Detection Using YOLO With Hybrid Feature Fusion
LDR:03218nam a22004453i 4500 001 1172921
005 20260622113224.5
006 m o d
007 cr|nu||||||||
008 260803s2025 miu||||||m |||||||eng d
020 $a 9798315766896
035 $a (MiAaPQD)AAI32001353
035 $a AAI32001353
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Das, Shijon, $e author. $3 1503561
245 1 0 $a Enhancing Real-Time Vehicle and Pedestrian Detection Using YOLO With Hybrid Feature Fusion $c Shijon Das. $h [eletronic resource] /
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (82 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 86-11.
500 $a Advisors: Fouda, Mostafa Committee members: Bodily, Paul; Wakjira, Tadesse G.
502 $b M.S. $c Idaho State University $d 2025.
520 # $a Real-time object detection is central to the development of intelligent transportation systems, autonomous vehicles, smart city monitoring, and pedestrian safety functionalities. Among several deep learning-based approaches, the You Only Look Once (YOLO) series of object detectors has been among the top choices for a long time due to the trade-off it has attained between accuracy and inference speed. This thesis gives an in-depth review and experimental analysis of YOLO versions 7-12, utilized for the use of real-time vehicle and pedestrian object detection. While earlier versions of YOLO were performance competitive, they were poor at occlusion, low-light, and detection of small objects. In order to overcome these weaknesses, this paper proposes a novel YOLOv12-hybrid feature fusion model that integrates transformer-based attention mechanisms, bidirectional multi-scale feature aggregation, and RGB, depth, and semantic segmentation cross-modal input fusion. Large-scale experiments were conducted on the COCO 2017 dataset, comparing each iteration of YOLO based on mean Average Precision (mAP), training loss convergence, and inference speed (FPS). The results establish that YOLOv12 surpasses previous models, with an mAP of 88.2% and over 47 FPS inference rates, and yet offers consistent detection in challenging urban settings. Contrast against the traditional and state-of-the-art models also indicates the dominance of YOLOv12 for real-world deployment. This work not only establishes the benchmark for YOLO detector development but also offers a scalable, accurate, and real-time enabled model structure tailored for safety-critical use cases in traffic monitoring, autonomous vehicles, and smart infrastructure systems.
546 $a English
590 $a School code: 0320
650 # 4 $a Robotics. $3 561941
650 # 4 $a Information technology. $3 559429
650 # 4 $a Computer science. $3 573171
653 # # $a Deep learning
653 # # $a Object detection
653 # # $a Hybrid feature fusion
653 # # $a Traffic systems
653 # # $a YOLO
690 $a 0984
690 $a 0489
690 $a 0800
690 $a 0771
710 2 # $a Idaho State University. $b College of Science and Engineering - Computer Science. $e degree granting institution. $3 1503562
720 1 $a Fouda, Mostafa $e degree supervisor.
773 0 # $t Masters Abstracts International $g 86-11.
790 $a 0320
791 $a M.S.
792 $a 2025
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32001353