Real-Time Surveillance System based on Facial Recognition using YOLOv5

Majeed, Fahad; Khan, Farrukh Zeeshan; Iqbal, Muhammad; Nazir, Maria

doi:10.1109/majicc53071.2021.9526254

Cited by 12 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning algorithms and frameworks for object detection are numerous and continue to evolve. However, the YOLO (You Only Look Once) framework provides the highest accuracy among other object detection, which makes it a state-of-the-art that beats other algorithms [1]. YOLO has various versions created by various publishers.…”

Section: Methodsmentioning

confidence: 99%

“…Muhammad Rizqi Sholahuddin 1 , Maisevli Harika 2 , Iwan Awaludin 3 , Yunita Citra Dewi 4 , Fachri Dhia Fauzan 5 , Bima Putra Sudimulya 6 , Vandha Pradiyasma Widarta 7 262 Significant advancements have been observed in object detection, primarily due to the rapid progress in artificial neural networks, particularly within the domain of neural networks. As a result, there have been notable advancements in detection algorithms that utilize deep learning techniques in recent years [2].…”

Section: Optimizing Yolov8 For Real-time Cctv Surveillance: a Trade-o...mentioning

confidence: 99%

“…Real-time surveillance refers to the continuous monitoring and analysis of activities and relevant data through a system of multiple Closed-Circuit Television (CCTV) cameras. This configuration, combined with a set of algorithms, is effective in identifying, tracking, and recognizing individuals in real-time video streams [1].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimizing YOLOv8 for Real-Time CCTV Surveillance: A Trade-off Between Speed and Accuracy

Sholahuddin,

Harika,

Awaludin

et al. 2023

join

View full text Add to dashboard Cite

Real-time video surveillance, especially CCTV systems, requires fast and accurate face detection. Object detection models with slow inference times are ineffective in real-time. This study addresses this challenge by improving the inference speed of the YOLOv8 model, a leading object detection framework known for its accuracy and speed. We focus on pruning the model's architecture, particularly the P5 head section, which detects larger objects. According to Bochkovskiy's 2020 research, this modification enhances the model's performance specifically for medium and small objects in CCTV footage. The standard YOLOv8 model and its modified version were compared for inference time, mean Average Precision (mAP), and model weight. The pruned YOLOv8 model cuts inference time by 15.56%, from 4.5 ms to 3.8 ms, and reduces model weight. The advantages mentioned above are offset by a 1.6% decrease in mean average precision. This research advances object detection technology by demonstrating architectural modifications' efficacy. These changes make the model faster and lighter, making it suitable for real-time surveillance. The accuracy trade-off is slight. The implications of these findings are crucial for implementing efficient object detection systems in CCTV surveillance. These findings also lay the groundwork for future research to improve such systems' speed-accuracy trade-off.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Optimizing Yolov8 For Real-time Cctv Surveillance: a Trade-o...mentioning

confidence: 99%