Method for the adaptive determination of a threshold value for the identification of vehicle lights using a camera system

• US 8,391,558 B2
• Filed: 10/16/2008
• Issued: 03/05/2013
• Est. Priority Date: 10/25/2007
• Status: Expired due to Fees

• Current Assignee: ADC GmbH (TE Connectivity Ltd. (United Kingdom))
• Original Assignee: ADC GmbH (TE Connectivity Ltd. (United Kingdom))
• Inventors: Fechner, Thomas, Almeida, Carlos, Schaale, Christian, Krkel, Dieter
• Primary Examiner(s): Tabatabai, Abolfazl
• Application Number:
  US12/739,477
• Publication Number:
  US 20100316258A1
• Time in Patent Office: 1,601 Days
• Field of Search: 382/104, 340/332, 340/457.2, 340/468, 340/545.3, 340/555, 340/641, 340/815.45, 340/815.66, 340/815.75, 340/815.77, 340/956, 340/982, 340/985, 701/1, 701/22, 701/36, 701/50, 348/148, 348/149
• US Class Current: 382/104
• CPC Class Codes: B60Q 1/1423 Automatic dimming circuits, i.e. switching between high beam and low beam due to change of ambient light or light level in road traffic
• CPC Class Codes: B60Q 2300/41 preceding vehicle
• CPC Class Codes: B60Q 2300/42 oncoming vehicle
• CPC Class Codes: G06V 20/584 of vehicle lights or traffic lights

Abstract

A method for determining at least one threshold value S for distinguishing, in the dark, between reflectors and vehicle lights that are recorded as light spots by a camera sensor oriented towards the surroundings of a vehicle. The camera sensor records a series of images of the surroundings of the vehicle. At least one light spot in the series of images is tracked. When the tracking of a light spot is completed, at least one parameter (for example the maximum intensity I_max of the light spot in the entire series of images, or the lifetime τ of the light spot) is determined from measured values, for example from the intensity of the light spot in each image. The threshold value S is then adapted to the determined parameter/s. The determined parameter value of the light spot is included in a frequency distribution of the parameter values from previously tracked light spots. A new threshold value for distinguishing between vehicle lights and reflectors is determined from the updated frequency distribution of the parameter values. After temporal filtering a new threshold value for distinguishing between reflectors and vehicle lights is fixed.

Claims

1. A method for determining at least one threshold value S for distinguishing, in the dark, between oncoming vehicle lights and reflectors that are recorded as light spots by a camera sensor oriented towards the surroundings of a vehicle, comprising:

recording a series of images of the surroundings of the vehicle with the camera sensor;

tracking at least one light spot in the series of images is tracked;

determining, after tracking of the at least one light spot is completed, at least one parameter of the at least one light spot in the series of images; and

adapting a threshold value S by;

including the determined at least one parameter value in a frequency distribution n for the parameter of several light spots that all have been tracked over several images;

determining, from the frequency distribution of the previously determined parameter values, a threshold value S_neu for distinguishing between vehicle lights and reflectors; and

fixing, after temporal filtering, a new threshold value S for distinguishing between reflectors and vehicle lights.

2. The method according to claim 1 wherein the temporal filtering is a temporal low-pass filtering.

3. The method according to claim 1, wherein the threshold value S_neu for distinguishing between reflectors and vehicle lights is determined from the frequency distribution n of the previously determined parameter values by applying methods of decision theory.

4. The method according to claim 1, wherein the maximum intensity I_max of a light spot is used as a parameter.

5. The method according to claim 4, wherein the lifetime τ

of a light spot is used as a second parameter.