Related Experiment Video
Updated: Feb 22, 2026
10:52
Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior
Published on: April 13, 2016
9.2K
On-Board Detection of Pedestrian Intentions
Zhijie Fang1,2, David Vázquez3, Antonio M López4,5
1Computer Science Department, Universitat Autònoma Barcelona (UAB), 08193 Barcelona, Spain. zfang@cvc.uab.es.
Sensors (Basel, Switzerland)
|September 27, 2017
Summary
This study introduces a novel vision-based method to predict pedestrian road-crossing intentions using pose analysis. This approach offers early warnings for advanced driver assistance systems (ADAS), enhancing road safety.
Area of Science:
- Computer Vision
- Robotics
- Artificial Intelligence
Background:
- Vehicle-to-pedestrian (V2P) crash avoidance is crucial for advanced driver assistance systems (ADAS) and autonomous vehicles.
- Deep learning has significantly improved pedestrian detection accuracy using visual data.
- Detecting pedestrian intentions, particularly road crossing, is vital for proactive safety measures but remains less explored than detection.
Purpose of the Study:
- To develop a vision-based approach for predicting pedestrian road-crossing intentions.
- To enable earlier detection of potential V2P crashes by anticipating pedestrian behavior.
Main Methods:
- Analyzing pedestrian pose across multiple video frames to infer crossing intent.
- Utilizing a monocular vision system, eliminating the need for stereo vision or optical flow.
Main Results:
- Achieved 750 milliseconds of anticipation for pedestrians crossing the road.
- This anticipation provides an additional 15 meters of reaction distance at 50 km/h compared to traditional pedestrian detectors.
Conclusions:
- The proposed method effectively predicts pedestrian road-crossing intentions from monocular video.
- This contributes to enhanced safety systems by providing earlier warnings for potential V2P collisions.
Related Concept Videos
01:05Difference from Background: Limit of Detection
8.6K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
The LOD indicates the presence or absence...
8.6K
01:11Direct Motor Pathways
4.7K
The direct motor pathways, also known as the pyramidal tracts, are a group of neural pathways that originate in the brain and descend through the spinal cord. They control the voluntary movement of the body. There are two major direct motor pathways: the corticospinal and the corticobulbar tracts.
The corticospinal tract is responsible for the voluntary movement of the limbs and trunk. It originates in the cerebral cortex of the brain and descends through the cerebrum's internal capsule and...
The corticospinal tract is responsible for the voluntary movement of the limbs and trunk. It originates in the cerebral cortex of the brain and descends through the cerebrum's internal capsule and...
4.7K
01:26PD Controller: Design
682
In automotive engineering, car suspension systems often employ Proportional Derivative (PD) controllers to enhance performance. PD controllers are utilized to adjust the damping force in response to road conditions. A controller, acting as an amplifier with a constant gain, demonstrates proportional control, with output directly mirroring input.
Designing a continuous-data controller requires selecting and linking components like adders and integrators, which are fundamental in Proportional,...
Designing a continuous-data controller requires selecting and linking components like adders and integrators, which are fundamental in Proportional,...
682