Night preceding vehicle detection method for heavy-duty truck
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology for heavy-duty trucks and vehicles ahead, applied in the field of vehicle safety, can solve the problems of not being able to filter out the interference of other bright areas, the influence of detection work, and the increase of difficulty, so as to achieve a simplified detection environment, high accuracy, and negative samples. Simplified effect
Active Publication Date: 2015-10-21
山东智瞰深鉴信息科技有限公司
View PDF3 Cites 8 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0007] However, when a heavy-duty truck is driving on a highway, it often travels fast, and the headlights of the truck are very bright, and there are also large areas of light on the road due to the bright headlights of the heavy-duty truck, road signs, road surfaces, guardrails, signs and other objects. Interference such as reflections also makes the taillights of vehicles driving in different lanes ahead appear asymmetrical, which greatly increases the difficulty of detecting vehicles in front of heavy trucks at night, making the above method unable to filter out other bright areas well. The interference will affect the follow-up detection work
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0050] A method for detecting a vehicle ahead of a heavy truck at night, the specific steps comprising:
[0051] A. Get the classifier
[0052] (1) During the driving process of the heavy truck, the driving environment in front of the heavy truck is photographed, and a large number of 8-bit grayscale images are obtained; figure 2 It is a schematic diagram of an image in the large number of 8-bit grayscale images;
[0053] (2) adopt the threshold value processing method to remove the interference in each frame of gray-scale image in a large amount of 8-bit gray-scale images that step (1) obtains; Remove figure 2 The schematic diagram of the image obtained after the interference in image 3 shown;
[0054] (3) In the grayscale image that step (2) obtains, intercept the positive sample of the headlight pair region as the training classifier, and intercept the non-car light pair region as the negative sample of the training classifier;
[0055] (4) using the positive sample ...
Embodiment 2
[0059] According to the method for detecting vehicles ahead of heavy trucks at night in Embodiment 1, the difference is that the threshold processing method specifically includes:
[0060] a. Calculate the grayscale image in the region of interest (0, N cols / m,N rows ,N cols ·(m-1) / m) pixel value mean μ l , the region of interest refers to: the position of the first pixel in the upper left corner is (0,N cols / m), the width is N rows , high as N cols ·(m-1) / m; the value of m is 3, and the value range of m makes the region of interest not include the sky part. mu l The calculation formula of is shown in formula (I):
[0061] μ l = m ( m - 1 ) · ( N c o l s ...
Embodiment 3
[0069] According to the method for detecting vehicles ahead of heavy trucks at night in Embodiment 2, the difference is that the local standard deviation σ in the small window is calculated i , the specific calculation formula is shown in formula (II):
[0070] σ i 2 = 1 | Ω | Σ ( x , y ) ∈ Ω [ I t ( x , y ) - μ i ] 2 - - - ( I I ) ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
Abstract
The invention discloses a night preceding vehicle detection method for heavy-duty trucks. The night preceding vehicle detection method comprises the steps of acquiring a classifier and realizing vehicle detection. Specifically, the classifier acquisition comprises the steps of: removing interference in a gray scale image of a driving environment in front of a heavy-duty truck by adopting a threshold value processing method; intercepting a vehicle-lamp-pair region as a positive sample, and intercepting non-vehicle-lamp-pair regions as negative samples; and training the positive sample and the negative samples by adopting an adaboost algorithm based on haar-like features to obtain the classifier. The vehicle detection realization comprises the steps of reading a current frame gray scale image of video in real time and executing the operations as following: removing the interference in the current frame gray scale image by adopting the threshold value processing method to obtain a detected and processed current frame gray scale image; loading the classifier; detecting a vehicle-lamp-pair region in the detected and processed current frame gray scale image; and marking the vehicle-lamp-pair region in a copy of the current frame gray scale image. The night preceding vehicle detection method for heavy-duty trucks removes tail lamp interference, preserves shape of the vehicle lamp pair perfectly, reduces interference, simplifies the number of samples, improves the detection rate of the classifier, marks the detection result in the original image, and verifies the practicability of the device.
Description
technical field [0001] The invention relates to a detection method for a vehicle ahead of a heavy truck at night, and belongs to the technical field of vehicle safety. Background technique [0002] The rapid development of the transportation and logistics industry brought about by the advancement of the economy and society has brought great convenience to the society and people's life. At the same time, the number of cars has increased sharply, which has led to the deterioration of road traffic conditions. The driver assistance system (DAS) can help the driver control the vehicle by analyzing the current driving environment of the vehicle, improve traffic safety and prevent accidents. The input of the assisted driving system is generally a digital image (such as from a CCD camera or a CMOS camera), an infrared image, a laser, a radar, an ultrasonic wave or a GPS signal. [0003] There are three main categories of traditional night vision technologies that have been put into...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more