Tăng hiệu quả phát hiện dị thường trên ảnh UAV ứng dụng trong công tác tìm kiến cứu nạn

0 Người đánh giá. Xếp hạng trung bình 0

Tác giả: Khánh Hoài Đào, Văn Phương Nguyễn, Minh Đức Tống

Ngôn ngữ: Vie

Ký hiệu phân loại: 629.8 Automatic control engineering

Thông tin xuất bản: Tạp chí Khoa học và Công nghệ Đại học Thái Nguyên, 2020

Mô tả vật lý: 58-65

Bộ sưu tập: Metadata

ID: 402791

Thêm vào giỏ Liên kết toàn văn

Hoạt động tìm kiếm và cứu nạn bao gồm việc tìm kiếm và giải cứu người, phương tiện bị mắc kẹt trong các tình huống khó khăn. Trong thời gian gần đây, một thiết bị được ứng dụng nhiều trong cả quân sự và dân sự là phương tiện bay không người lái (UAV), nó thực sự là một nguồn lực rất lớn cho sứ mệnh tìm kiếm cứu nạn. Bởi thiết bị này có thể mang cảm biến hình ảnh có độ phân giải cao, phạm vi hoạt động rộng, địa hình đa dạng mà không cần quá nhiều nhân lực và chi phí cho quá trình tìm kiếm. Tuy nhiên, với số lượng lớn ảnh thu được từ thiết bị này, kết hợp với độ phân giải cao trong một khu vực rộng lớn là rào cản không hề nhỏ để phát hiện bằng mắt thường. Tự động phát hiện mục tiêu là giải pháp phù hợp. Để tránh bỏ sót các mục tiêu, tăng hiệu quả phát hiện của các thuật toán là cần thiết. Trong nghiên cứu này, chúng tôi đề xuất một phương pháp tăng hiệu quả phát hiện mục tiêu của quy tắc quyết định dựa trên kiểm tra tỷ lệ khả năng sử dụng mô hình phi tham số để ước tính hàm mật độ xác suất của dữ liệu nền bằng cách kết hợp kết hợp với các kỹ thuật: khử nhiễu
trích rút đặc trưng SIFT, SURF. Kết quả thử nghiệm trên bộ dữ liệu mẫu cho kết quả khác biệt rõ rệt, nhất là các trường hợp ảnh bị can nhiễu., Tóm tắt tiếng anh, Search and rescue activities include finding and rescuing people and vehicles trapped in difficult. In recent times, unmanned aerial vehicles (UAV) have been used in both military and civilian applications. It is a huge resource for the search and rescue mission. Because this device can carry high-resolution image sensors, a wide range of activities, diverse terrain without too many cores force and cost for the search process. However, the large number of images obtained and combined with high resolution in a large area of a scene is a great barrier to detect with the naked eyes. Therefore, automatic target detection is the right solution. To avoid missed targets, increasing the detection efficiency of the algorithms is necessary. In this study, we propose a method to increase the efficiency anomaly detection of the decision rule based on the ratio test of the ability to use a non-parametric model to estimate the probability density function of the background data by combining with techniques: noise cancellation
SIFT, SURF feature extraction. Test results on the sample data set showed noticeable differences, especially in the case of image noise.

1. Đọc trực tuyến

1. Đọc trực tuyến

Tạo bộ sưu tập với mã QR