Closed saleena-18 closed 1 month ago
Thank you for raising a issue, Hope you enjoing the open source. we try to reply or assign as soon possibe. Connect with mentor.
I am a GSSOC '24 Contributor I agree to follow the project's Code of Conduct Can you please label this issue for 'gssoc' and the 'level.' I'd love to work on this issue since I have prior knowledge of working on YOLO models with Face Detection algorithms. This would be practically helpful for the Government too for traffic surveillance in case of non-adherence to traffic rules on roads and highways. I promise to work diligently on the project.
Approach:
Perform Transfer Learning and fine-tune our CNN/deep learning model using YOLOv7 architecture. Implement OCR text detection and extraction to predict vehicle numbers from video and image inputs. Utilize YOLOv7's high speed to enable real-time video input, making it suitable for practical applications like traffic surveillance systems, where traditional CNN models would lag. I am eager to bring my expertise in machine learning and deep learning to this project, and I am confident that this approach will significantly enhance the model's performance and real-time applicability.
We dont required as our project is heading towards movie review
Problem: Traditational CNN models are much slower than YOLOv7 due their complex multi-stage pipeline
Solution: YOLOv7 is 509% faster and has 2% higher accuracy than Mask-R CNN Model It requires several times cheaper hardware than other neural networks and can be trained much faster on small datasets without any pre-trained weights.
Approach: We will perform Transfer Learning and fine-tune our CNN (convolutional neural network)/ deep learning model using the yolov7 architecture. Then after performing OCR text detection and extraction, the model will be able to predict vehicle number by taking video and image input.
Further, we can make this take real time video input since YOLO models because of their high speed can be easily used for real-time object detection which can be implemented in practical scenarios such as traffic surveillance systems, whereas CNN models would lag in such a case.