.png){kind=icon}
.png){kind=icon}
Return
Computational Intelligence for Detecting Pedestrian Movement Patterns
.png){kind=icon}
PRE
AI
DOI：10.1007/978-3-030-12804-3_12.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The article presents a system that uses computational intelligence to detect pedestrian movement patterns by applying image processing and pattern detection. The system is capable of processing in real time multiple image/video sources and it is based on a pipes and filters architecture that makes it easy to evaluate different computational intelligence techniques. The system counts with two main stages: the first stage extracts the relevant features of images and the second stage is responsible for the detection of patterns. The experimental analysis performed over more than 1450 problem instances covers the two main stages of the system. The system was evaluated using PETS09-S2L1 videos and the results were compared with part of the MOTChallenge benchmark results. Results suggest that the proposed system is competitive, yet simpler, than other similar software methods.
Keywords:
Computational intelligence
Image processing
Pedestrian movement patterns
Surveillance cameras
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
5.5
Papers:
929
Citations:
3.0K