• Sudha K
• Vanitha J C
• Mudukur Swetha

Real-time vehicle detection, tracking, and counting are critical components of modern traffic monitoring and intelligent transportation systems. Effective traffic flow management on urban highways depends on continuous, accurate, and real-time analysis of vehicle movement to reduce congestion, detect violations, and prevent accidents. This paper presents an enhanced system based on a modified YOLOv7 model designed specifically for real-time traffic surveillance on urban roads and highways. The proposed approach addresses key challenges in traditional object detection methods, such as high missed detection rates, limited recognition of small and distant vehicles, and insufficient feature extraction in complex traffic scenes. The core tasks of the system include detecting moving vehicles, tracking them across frames, categorizing different vehicle types, and accurately counting them to generate meaningful statistical traffic data. A modified YOLOv7 architecture is implemented to improve detection accuracy by refining feature extraction and enhancing the model’s sensitivity to small-scale targets. The system processes live video feeds from CCTV or traffic cameras and outputs real-time metrics on traffic flow, vehicle density, and class-wise counts. Through extensive experimentation on urban highway scenarios, the proposed method demonstrates significant improvements in precision and reliability over existing models. The resulting data provides actionable insights for city planners, traffic authorities, and safety analysts. This framework not only aids in dynamic traffic control but also contributes to long-term infrastructure planning and intelligent transportation strategies. The enhanced YOLOv7-based system thus offers a scalable, efficient, and highly accurate solution for real-time vehicular monitoring in urban environments.

Real-time vehicle detection, tracking, and counting are critical components of modern traffic monitoring and intelligent transportation systems. Effective traffic flow management on urban highways depends on continuous, accurate, and real-time analysis of vehicle movement to reduce congestion, detect violations, and prevent accidents. This paper presents an enhanced system based on a modified YOLOv7 model designed specifically for real-time traffic surveillance on urban roads and highways. The proposed approach addresses key challenges in traditional object detection methods, such as high missed detection rates, limited recognition of small and distant vehicles, and insufficient feature extraction in complex traffic scenes. The core tasks of the system include detecting moving vehicles, tracking them across frames, categorizing different vehicle types, and accurately counting them to generate meaningful statistical traffic data. A modified YOLOv7 architecture is implemented to improve detection accuracy by refining feature extraction and enhancing the model’s sensitivity to small-scale targets. The system processes live video feeds from CCTV or traffic cameras and outputs real-time metrics on traffic flow, vehicle density, and class-wise counts. Through extensive experimentation on urban highway scenarios, the proposed method demonstrates significant improvements in precision and reliability over existing models. The resulting data provides actionable insights for city planners, traffic authorities, and safety analysts. This framework not only aids in dynamic traffic control but also contributes to long-term infrastructure planning and intelligent transportation strategies. The enhanced YOLOv7-based system thus offers a scalable, efficient, and highly accurate solution for real-time vehicular monitoring in urban environments.

"ENHANCED REAL-TIME VEHICLE DETECTION, TRACKING, AND COUNTING ON URBAN HIGHWAYS USING YOLOV7", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 10, page no.f191-f198, October-2022, Available :http://www.jetir.org/papers/JETIR2210534.pdf

"ENHANCED REAL-TIME VEHICLE DETECTION, TRACKING, AND COUNTING ON URBAN HIGHWAYS USING YOLOV7", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 10, page no. ppf191-f198, October-2022, Available at : http://www.jetir.org/papers/JETIR2210534.pdf