Fisheye Human Detection via Head-Body Pairing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing methods for detecting people using fisheye camera images face challenges such as increased processing costs and delays due to preprocessing for distortion correction, and suffer from false detection risks, especially when objects at image boundaries are processed, leading to reduced detection accuracy.
Innovation Solution
A human detection system that analyzes fisheye images without plane development, using a head detector and a human body detector to identify candidates, and a determining unit to validate pairs based on prescribed conditions such as overlap, size ratios, and detection reliability, ensuring accurate person detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the fisheye image is developed in a plane to eliminate distortion, then detection accuracy is improved, but processing time increases and real-time detection becomes difficult
Solution Approach 1:
Instead of developing the fisheye image into a plane to eliminate distortion, the invention inverts the approach by performing detection processing directly on the distorted fisheye image. The determination unit evaluates multiple detection results from different algorithms and selects the most reliable one, achieving accurate detection without time-consuming preprocessing.
2Reliability
If the fisheye image is developed in a plane, then distortion is eliminated, but false detection increases due to deformation or division of objects at image boundaries
Solution Approach 1:
The invention introduces a determination unit as an intermediary that mediates between multiple detection algorithms. This unit evaluates detection results from different algorithms, compares them, and selects the most reliable detection result, thereby reducing false detections caused by boundary effects in plane development.
3Productivity
If detection processing is performed on the fisheye image without plane development, then processing speed is improved, but detection accuracy decreases due to variations in appearance of detected objects
Solution Approach 1:
The invention merges multiple detection algorithms and their results into a unified evaluation process. The determination unit combines detection results from different algorithms, evaluates their reliability, and selects the best result, thereby maintaining high detection speed while improving accuracy despite appearance variations in fisheye images.
4Reliability
If multiple detection algorithms are used to improve accuracy, then detection reliability is improved, but processing complexity increases
Solution Approach 1:
The invention changes the parameter of algorithm selection dynamically based on image characteristics and detection requirements. The determination unit evaluates detection results from multiple algorithms and selects the most appropriate one for each specific case, achieving high reliability without permanently increasing system complexity.
Data Source
AI summary
A human detection device configured to analyze a fisheye image obtained by a fisheye camera installed above a to-be-detected area to detect a person existing in the to-be-detected area includes a head detector configured to detect at least one head candidate from the fisheye image by using an algorithm for detecting a human head, a human body detector configured to detect at least one human body candidate from the fisheye image by using an algorithm for detecting a human body, and a determining unit configured to determine, as a person, a pair satisfying a prescribed condition among pairs of the head candidate and the human body candidate formed of a combination of a detection result from the head detector and a detection result from the human body detector.