MÔ HÌNH TOÁN HỌC CHO BÀI TOÁN PHÂN LOẠI CÁC KHUYẾT TẬT MẶT ĐƯỜNG

0 Người đánh giá. Xếp hạng trung bình 0

Tác giả: Tuấn Dũng Kiều, Quang Hiệp Nguyễn, Thị Dung Nguyễn, Thị Phương Dung Nguyễn, Thị Liên Phạm, Thị Tuyết Trần

Ngôn ngữ: vie

Ký hiệu phân loại:

Thông tin xuất bản: Tạp chí Khoa học và Công nghệ - Đại học Thái Nguyên, 2022

Mô tả vật lý: tr.50 - 60

Bộ sưu tập: Metadata

ID: 332640

Thêm vào giỏ Liên kết toàn văn

Hệ thống phân loại và phát hiện khuyết tật mặt đường dựa trên thuật toán máy học vốn đã rất tiên tiến và ngày càng chứng tỏ những ưu điểm vượt trội của mình. Trong bài báo này, một số thuật toán phân đoạn hình ảnh được sử dụng trong thực tế được trình bày, so sánh và đánh giá. Trong nghiên cứu này, chúng tôi trình bày mạng nơ-ron tích chập - cấu trúc VGG16 để phân loại các khuyết tật mặt đường, với phương pháp dựa trên đồ thị để tối ưu hóa việc phân đoạn hình ảnh trên hình ảnh khuyết tật mặt đường. Phương pháp đề xuất này nhằm khắc phục những hạn chế do các yếu tố khách quan gây ra, chẳng hạn như độ nhạy cao đối với dữ liệu của một số loại phụ thuộc vào ánh sáng và tiếng ồn, chẳng hạn như dữ liệu khuyết tật của mặt đường. Ba bộ dữ liệu khác nhau được thu thập từ Trung tâm Viễn thông và Đa phương tiện, INESC TEC - Bồ Đào Nha (1200 hình ảnh), thành phố Irkutsk - Liên bang Nga (800 hình ảnh) và thành phố Thái Nguyên - Việt Nam (550 hình ảnh). Kết quả phân lớp dựa trên các phương pháp VGG-16 của lần lượt các bộ dữ liệu cho thấy kết quả phân loại là tốt vì các đường cong có trạng thái gần giá trị 1 hơn giá trị 0,5.The road surface defect detection and classification system based on machine learning algorithms is already very advanced and is increasingly proving its outstanding advantages. In this paper, some image segmentation algorithms used in practice are presented, compared and evaluated. In this study, we present the convolution neural network—VGG16 structure to classify pavement defects, with a graph-based method to optimize the image segmentation on the pavement defect image. This proposed method is intended to overcome limitations caused by objective factors, such as high sensitivity to data of certain types of light and noise dependence, such as defect data of the road surface. Three different datasets were collected from the Center for Telecommunication and Multimedia, INESC TEC - Portugal (1200 images), Irkutsk city - Russian Federation (800 images) and Thai Nguyen city - Vietnam (550 images). The classification results based on the VGG-16 methods of the datasets in turn are good because the curves have a state closer to 1 than 0.5.

1. Đọc trực tuyến

1. Đọc trực tuyến

Tạo bộ sưu tập với mã QR