Target detection algorithm based on multi-feature extraction and multitask fusion

Abstract

The invention relates to a target detection algorithm based on multi-feature extraction and multitask fusion. The technical characteristics of the target detection algorithm are that image features are extracted based on a deep learning convolutional neural network framework, the multilayer convolutional output result is extracted to form a multi-feature graph, and target areas-of-interest of different horizons are extracted from the multi-feature graph and feature connection is performed; semantic segmentation of the original graph is performed and the target segmentation area result is extracted, and multitask cross auxiliary target detection is performed on the target detection result and the target segmentation result in full connection layers through certain proportionality coefficient; and the result passes through the last full connection layer and then the image features are classified and regressively positioned through the combination classification and positioning loss function so that the final target detection result can be obtained. High-precision target detection positioning and classification can be realized by feature extraction through the deep learning convolutional neural network, multi-group and multilayer fusion and connection of the image features and loss function combination so that the great target detection result can be obtained.

Description

technical field [0001] The invention belongs to the technical field of target detection, in particular to a target detection algorithm based on multi-feature extraction and multi-task fusion. Background technique [0002] The main task of target detection is to automatically detect target objects in image sequences, including classification and localization. The current popular target detection algorithm first generates 1K-2K candidate boxes on a picture, and then uses CNN convolutional neural network to extract features for each candidate box, and then inputs the features into each class of SVM classifier or Softmax classification The regressor is used to determine whether the target belongs to this category, and finally the regressor is used to correct the position of the candidate frame to achieve precise positioning of the target. The traditional target detection algorithm uses features such as SIFT, HOG and LBP, and realizes the matching between images by finding the i...

AI Technical Summary

Problems solved by technology

Although researchers have proposed many target detection algorithms based on deep learning convolutional neural networks, and these algorithms have achieved good results, there are still many aspects to be improved, such as complex picture background, fixed network input size, too many candidate frames, Problems such as slow training speed, computer memory consumption, inaccurate detection of small objects, cumbersome steps, and inaccurate positioning

Images