Radar based tracking of slow moving objects

Abstract

An illustrative example method of classifying a detected object (22) includes detecting an object (22), determining that an estimated velocity of the object (22) is below a preselected threshold velocity requiring classification, determining a time during which the object (22) has been detected, determining a first distance the object (22) moves during the time determining a speed of the object (22) from the first distance and the time, determining a second distance that a centroid of the detected object (22) moves during the time, and classifying the detected object (22) as a slow moving object or a stationary object based on a relationship between the first and second distances and a relationship between the estimated velocity and the speed.

Description

Background technique [0001] Modern vehicles include a variety of sensors and detectors that provide information about the vehicle's surroundings or vicinity. For example, radar tracking devices provide information about the vehicle's vicinity or objects in its path. Such information is useful for driver assistance features. In some cases, automatic or semi-autonomous vehicle operation may be enabled based on such information. For example, adaptive cruise control and park assist features are known that automatically control the speed or movement of the vehicle based on such sensor input. Self-driving autonomous or autonomous vehicles can utilize such information. [0002] While radar and other sensor devices have proven useful, there are limitations to the type or accuracy of information that can be obtained from them. For example, sensors have limitations at lower rates, especially when there is little relative movement between the sensor and the object being tracked. Whe...

AI Technical Summary

Problems solved by technology

[0002] while radar and other sensor devices have proven useful, there are limitations to the type or accuracy of information that can be obtained from them

For example, sensors have limitations at lower rates, especially when there is little relative movement between the sensor and the object being tracked

Detections from radar devices can be ambiguous when objects are moving at low rates, making it difficult to classify objects as moving or stationary

Because of these ambiguous detections, the recognition of slow-moving objects (e.g., pedestrians or slow-moving cyclists) can be a challenging task

Images