Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Marine weak and small moving ship real-time detection method based on deep learning

A deep learning and real-time detection technology, applied in neural learning methods, instruments, biological neural network models, etc., can solve the problems that the recognition algorithm is difficult to achieve the recognition results, the line of sight is blocked, and the reliability and practicability of the weak and small target detection system are affected.

Active Publication Date: 2019-05-21
SHANGHAI MARITIME UNIVERSITY
View PDF7 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the lack of available information of the weak target image and its susceptibility to noise, the complex and changeable weather environment on the sea causes the line of sight to be blocked, etc., it is difficult for many recognition algorithms to achieve satisfactory recognition results, which seriously affects the reliability and reliability of the weak target detection system. practicability, so the research topic of real-time detection of weak and small moving ships at sea has great practical significance

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Marine weak and small moving ship real-time detection method based on deep learning
  • Marine weak and small moving ship real-time detection method based on deep learning
  • Marine weak and small moving ship real-time detection method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In order to make the technical means, creative features, goals and effects achieved by the present invention easy to understand, the present invention will be further described below in conjunction with the accompanying drawings, but the embodiments of the present invention are not limited thereto.

[0028] The present invention proposes a new network structure that refers to the SELU activation function. The main frame of the network structure is based on the YOLOv3 algorithm, and draws lessons from the simple structure of YOLOv2 to selectively remove the redundant residual network structure to maintain the effective efficiency of small targets. information to improve detection speed. as attached figure 1 As shown, the structure of this algorithm is a fully convolutional network type, which consists of 8 layers of convolutional neural networks. This network can be roughly divided into two parts. The first part is the first 5-layer network, which is used to extract the...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a marine weak and small moving ship real-time detection method based on deep learning. The method comprises the steps: step 1, carrying out target detection processing on an image in a marine monitoring system video; step 2, performing size unification operation on the size of the input image; step 3, extracting small target features by using the first part of the networkstructure; and step 4, for the extracted features, learning the effective features of the small targets from the shallow network by using the classifier of the second part of the network structure, and then integrating the position information of the deep network to finally classify the small targets, wherein the network structure is of a full convolutional network type and comprises two parts, and the first part is used for extracting effective features of a target; and the second part is used for detecting a target and determining a final detection result.

Description

technical field [0001] The invention belongs to target detection and tracking technology, and in particular relates to an efficient detection method for weak and small targets in RGB color images with relatively single background and various infrared images. Background technique [0002] Object detection is a prerequisite for various advanced vision tasks and is widely used in various image processing tasks. Existing target detection technologies, such as face detection and pedestrian detection, have already had very mature application solutions. Relatively speaking, there is no very mature application solution for the detection of weak and small moving ships. Generally speaking, the target detection of weak and small moving ships is mainly used in the intelligent monitoring system. Due to the continuity of the monitoring system and the suddenness of the situation, manual monitoring cannot be vigilant at all times, which is prone to negligence and incalculable losses. Theref...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
Inventor 周薇娜丁豪文
Owner SHANGHAI MARITIME UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products