Radar/camera advanced detection and tracking

Developing radar/camera-based advanced detection and tracking algorithms in the context of applications for smart urban mobility - generating inputs for simulators; covering potentially problematic situations; testing accuracy and reliability of detectors; testing perception robustness under uncertainty; integrating simulation-based testing in continuous integration contexts
VALU3S_WP1_Automotive_1
Covering potentially problematic situations, testing accuracy and reliability of detector algorithms
Evaluation Scenario Requirements
V&V Methods
VALU3S Framework
Contents
UC1_R_1

Road users counting accuracy should be at least 99%

UC1_R_2

Speed measurement error shall be within 2kph for speed up to 100kph and 2% for speed over 100kph.

UC1_R_3

System should keep its qualities even in bad/tricky lighting and weather conditions.

UC1_R_4

Radar sensor automatic configuration/calibration should provide good estimation of installation parameters (azimuth, elevation, rotation - within 1 degree accuracy, mounting height - within 10cm accuracy) including detection of manipulation with the sensor.

UC1_R_5

Robustness under sensor faults

UC1_R_6

System shall properly detect and track two vehicles going side by side at the very similar relative speed.

UC1_R_7

Radar sensor shall detect and track weak objects (in terms of radar signal power reflection) such as cyclists in the presence of strong reflectors such as vehicles including being able to classify them.

UC1_R_8

System shall detect and track slowing down traffic including detection of presence of static/stopped vehicles (even crashes which are definitely safety issue).

UC1_R_9

System shall detect and track vehicle going at very high speed including less than 2% speed error.

UC1_R_10

System shall detect and track driving in opposite direction (wrong way - safety issue).