Pedestrian detection method, system and terminal for multi-modal information fusion in image

Abstract

The invention discloses a pedestrian detection method, system and terminal for multi-modal information fusion in an image. The method comprises the steps of obtaining a corresponding top view according to an original head-up view; predicting a pedestrian target probability and a pedestrian target frame width for each point on the top view; obtaining a corresponding depth map through the head-up image, and estimating the height of a pedestrian target frame based on the depth; integrating the pedestrian target frame width and the pedestrian target frame height into a target candidate frame, anduniformly encoding the target candidate frame to a semantic space through an encoder to obtain a pedestrian target probability under a head-up view; and performing weighted average on the pedestrian target probabilities of the head-up view and the top view to obtain a final pedestrian target prediction result. According to the method, the pedestrian shielding problem under a head-up view angle iseffectively avoided, complex background interference is effectively removed, the method is suitable for variable situations in a real application environment, the detection robustness is enhanced, thefalse detection and missing detection probability is reduced, and the detection capability of pedestrian targets in video images is effectively improved.

Description

Technical field [0001] The invention relates to the field of target detection in images, and in particular to a pedestrian detection method, system and terminal for multimodal information fusion in images. Background technique [0002] The advent of the era of big data has promoted the continuous update and development of computer technology. As a research hotspot in the field of computer vision, pedestrian detection technology has shown important application values ​​in the fields of intelligent video surveillance and intelligent transportation. Existing pedestrian detection methods, due to the following difficulties and challenges, the detection results need to be improved: due to the shooting distance, the picture is larger but the target pedestrian size is small, and the features of the target area are reduced by deep learning convolutional neural networks. Rarely, it is difficult to carry out effective detection and identification; due to the fixed shooting angle, the pedest...

AI Technical Summary

Problems solved by technology

However, there are still some problems. On the one hand, this method still uses the features of the entire target candidate box, and does not fully extract the body part features. In addition, it pays too much attention to the body part features or the features of the entire candidate box, resulting in the network in the global The imbalance between local and local, so the detector does not have good generalization performance; on the other hand, using a part detector to extract body part features will introduce additional labeled body part information, resulting in an increase in cost

Images