CN105744156A - System and method for improving object identification in image - Google Patents

System and method for improving object identification in image Download PDF

Info

Publication number
CN105744156A
CN105744156A CN 201610066335 CN201610066335A CN105744156A CN 105744156 A CN105744156 A CN 105744156A CN 201610066335 CN201610066335 CN 201610066335 CN 201610066335 A CN201610066335 A CN 201610066335A CN 105744156 A CN105744156 A CN 105744156A
Authority
CN
Grant status
Application
Patent type
Prior art keywords
image
exposure
current frame
current
analysis
Prior art date
Application number
CN 201610066335
Other languages
Chinese (zh)
Inventor
张开岭
Original Assignee
深圳市美好幸福生活安全系统有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00Details of television systems
    • H04N5/222Studio circuitry; Studio devices; Studio equipment ; Cameras comprising an electronic image sensor, e.g. digital cameras, video cameras, TV cameras, video cameras, camcorders, webcams, camera modules for embedding in other devices, e.g. mobile phones, computers or vehicles
    • H04N5/225Television cameras ; Cameras comprising an electronic image sensor, e.g. digital cameras, video cameras, video cameras, camcorders, webcams, camera modules for embedding in other devices, e.g. mobile phones, computers or vehicles
    • H04N5/232Devices for controlling television cameras, e.g. remote control; Control of cameras comprising an electronic image sensor, e.g. digital cameras, video cameras, TV cameras, video cameras, camcorders, webcams, camera modules for embedding in, e.g. mobile phones, computers or vehicles
    • H04N5/23216Control of parameters, e.g. field/angle of view of camera via graphical user interface, e.g. touchscreen
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00Details of television systems
    • H04N5/222Studio circuitry; Studio devices; Studio equipment ; Cameras comprising an electronic image sensor, e.g. digital cameras, video cameras, TV cameras, video cameras, camcorders, webcams, camera modules for embedding in other devices, e.g. mobile phones, computers or vehicles
    • H04N5/225Television cameras ; Cameras comprising an electronic image sensor, e.g. digital cameras, video cameras, video cameras, camcorders, webcams, camera modules for embedding in other devices, e.g. mobile phones, computers or vehicles
    • H04N5/235Circuitry or methods for compensating for variation in the brightness of the object, e.g. based on electric image signals provided by an electronic image sensor
    • H04N5/2353Circuitry or methods for compensating for variation in the brightness of the object, e.g. based on electric image signals provided by an electronic image sensor by influencing the exposure time, e.g. shutter

Abstract

The invention is suitable for the field of traffic safety early-warning systems, and provides a system for improving object identification in an image. The system comprises a camera module, an image acquisition module, an image analysis module and a control module. The camera module shoots all objects in front of the current car to obtain a first current frame image. The image acquisition module obtains the first current frame image. The image analysis module analyzes the first current frame image and computes the overexposure or underexposure degree of the first current frame image. The control module adjusts exposure parameters of the camera module according to the overexposure or underexposure degree. The camera module shoots again according to the adjusted exposure parameters in order to obtain a second current frame image. The image acquisition module obtains the second current frame image. The image analysis module analyzes the second current frame image and computes all objects of the second current frame image to establish a data set of all the objects. The data set of all the objects can be used for analytical calculation of traffic safety early-warning. The invention also provides a method for improving object identification in the image.

Description

一种提高影像中物体识别的系统及方法 A system and method for object recognition to improve image

技术领域 FIELD

[0001]本发明属于行车安全预警系统领域,尤其涉及一种提高影像中物体识别的系统中提高影像中物体识别的系统及方法。 [0001] The present invention belongs to the field of traffic safety warning system, particularly to an improved system and method for object recognition object image in the image recognition system is improved.

背景技术 Background technique

[0002]随着私家车的大量普及,越来越多的车辆在路上行驶,道路的复杂程度也越来越严重,行车安全就成了一个重要的课题。 [0002] With the increasing popularity of private cars, an increasing number of vehicles on the road, the road more and more serious degree of complexity, traffic safety has become an important issue. 现在基于视觉的提高影像中物体识别的系统是最有效、最安全的方法。 Now improve the image of the visual object recognition system is based on the most effective, most secure method. 然而由于基于视觉的提高影像中物体识别的系统容易受周围环境光线强度的影响。 However, due to susceptible ambient light intensity based imaging system to improve the visual object recognition. 若光线太暗,摄像头所拍摄的影像曝光不足,拍摄的影像中的物体的颜色与背景的颜色相差太小,导致提高影像中物体识别的系统很难识别当前车辆前方的全部物体。 If the light is too dark, the camera is less than the exposure of the recorded image, color and background color of the captured image of the object difference is too small, resulting in improved image object recognition system is difficult to identify all of the current object in front of the vehicle. 若光线太强,摄像头所拍摄的影像曝光过度,同样会导致提高影像中物体识别的系统很难识别当前车辆前方的全部物体。 If the light is too strong, the camera captured the image overexposed also leads to an increase in image object recognition system is difficult to identify all of the current object in front of the vehicle. 有时虽然周围环境的光线强度正常,但当前车辆前方的部分车辆却被建筑物(比如高架桥)的阴影遮挡,所以仍然会导致提高影像中物体识别的系统很难识别当前车辆前方的全部物体。 Although sometimes shaded normal ambient light intensity, but part of the vehicle is currently ahead of the vehicle was the building (such as viaducts) shielding, it still leads to an increase in image object recognition system is difficult to identify all of the current object in front of the vehicle. 因此如何在上述的多种情况下均能有效识别到当前车辆前方的全部物体,就变成了亟待解决的问题。 So how can effectively identify the variety of circumstances above all to the current object in front of the vehicle, it becomes a serious problem.

发明内容 SUMMARY

[0003]本发明所要解决的技术问题在于提供一种提高影像中物体识别的系统及方法,旨在能够有效识别当前车辆前方的全部物体。 [0003] The present invention solves the technical problem to provide a system and method for improved object recognition image, can effectively identify all currently aimed object in front of the vehicle.

[0004]本发明是这样实现的,一种提高影像中物体识别的系统,其包括摄像模块、影像获取模块、影像分析模块及控制模块。 [0004] The present invention is achieved, for improving the image of the object recognition system, which includes a camera module, the image acquisition module, the image analysis module and a control module. 该摄像模块用于拍摄一个当前车辆前方的全部物体,以得到一个第一当前帧影像。 The entire camera module for capturing a current object ahead of the vehicle, to obtain a first image of the current frame. 该影像获取模块用于获取该第一当前帧影像。 The image acquisition module for acquiring the first image of the current frame. 该影像分析模块用于对该第一当前帧影像进行曝光分析,若该第一当前帧影像属于整体曝光不正常,则计算出该第一当前帧影像过曝或欠曝的程度。 The image analysis module for performing analysis of the exposure of the first image of the current frame, if the current frame is the first image belonging to overall exposure is not normal, the calculated first image of the current frame under or overexposed degree of exposure. 该控制模块根据该第一当前帧影像过曝或欠曝的程度调整该摄像模块的曝光参数。 The first control module of the current frame image is overexposed or under-exposed extent of the adjustment of the exposure parameters of the camera module according to. 该摄像模块根据调整后的曝光参数再次拍摄该当前车辆前方的全部物体,以得到第二当前帧影像。 The imaging module according to the adjusted exposure parameter photograph the entire object is currently ahead of the vehicle again to obtain a second image of the current frame. 该影像获取模块用于获取该第二当前帧影像。 The image acquisition module for acquiring the second image of the current frame. 该影像分析模块还用于对该第二当前帧影像进行曝光分析,若该第二当前帧影像整体曝光正常,则对该第二当前帧影像中的全部物体进行分析计算,以构建全部物体数据集,使得一个行车安全预警系统中的安全预警分析模块能够根据该全部物体数据集进行行车安全预警的分析计算。 The image analysis module is further used for the current frame, a second image exposure analysis, if the second overall exposure of the current frame image is normal, a second object of the entire image of the current frame analysis and calculation, in order to construct the entire object data set, so that a traffic safety warning system warning safety analysis calculated analysis module capable of driving safety warning based on the entire set of data objects.

[0005]本发明还提供了一种提高影像中物体识别的方法,其包括如下步骤:使用一个摄像模块拍摄一个当前车辆前方的全部物体,以得到一个第一当前帧影像;获取该第一当前帧影像;对该第一当前帧影像进行曝光分析;若该第一当前帧影像属于整体曝光不正常,则计算出该第一当前帧影像整体过曝或欠曝的程度;根据该第一当前帧影像整体过曝或欠曝的程度调整该摄像模块的曝光参数;该摄像模块根据调整后的曝光参数再次拍摄该当前车辆前方的全部物体,获取一个第二当前帧影像;对该第二当前帧影像进行曝光分析;若该第二当前帧影像属于整体曝光正常,则对该第二当前帧影像中的全部物体进行分析计算,以构建全部物体数据集,该全部物体数据集能够被用于行车安全预警的分析计算。 [0005] The present invention further provides a method of object recognition enhanced images, comprising the steps of: using a camera module capturing a full current object ahead of the vehicle, to obtain a first image of the current frame; a first obtaining the current frame image; exposing a first analysis of the current frame image; if the first frame of the current image belongs overall exposure is not normal, the calculated first degree of the current frame image entirety of overexposed or underexposed; based on the first current overexposed image frames overall degree of exposure or under-exposure parameter to adjust the camera module; exposing the imaging module in accordance with the adjusted parameters of the photographed object in front of all the current vehicle again, obtaining a second image of the current frame; the second current analyzing image exposure frames; if the second image of the current frame belongs to the normal global exposure, the whole of the second object in the current frame image analysis and calculation, in order to construct the entire object data set, the entire set of data objects can be used analysis of traffic safety warning calculations.

[0006]本发明与现有技术相比,有益效果在于:本发明的提高影像中物体识别的系统及方法,能够有效识别当前车辆前方的全部物体,以更好地对驾驶者进行保护。 [0006] Compared with the prior art, the beneficial effects that: the object recognition system and method of the present invention improve the image, it is possible to identify all currently active object in front of the vehicle, in order to better protect the driver.

附图说明 BRIEF DESCRIPTION

[0007]图1是本发明较佳实施例提供的提高影像中物体识别的系统的功能模块图。 [0007] FIG. 1 is a functional block diagram of a system to improve the image of the object recognition provided by the preferred embodiment of the present invention.

[0008]图2及图3是本发明较佳实施例提供的提高影像中物体识别的方法的流程图。 [0008] FIG. 2 and FIG. 3 is a flowchart of a method to improve the image of the object recognition provided by the preferred embodiment of the present invention.

具体实施方式 detailed description

[0009]为了使本发明的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本发明进行进一步详细说明。 [0009] To make the objectives, technical solutions and advantages of the present invention will become more apparent hereinafter in conjunction with the accompanying drawings and embodiments of the present invention will be further described in detail. 应当理解,此处所描述的具体实施例仅仅用以解释本发明,并不用于限定本发明。 It should be understood that the specific embodiments described herein are only intended to illustrate the present invention and are not intended to limit the present invention.

[0010]如图1所示,本发明较佳实施例所提供的一种提高影像中物体识别的系统100,其包括摄像模块101、影像获取模块10、影像分析模块20及控制模块30。 [0010] As shown in FIG 1, in the preferred embodiment to an image object recognition system improved embodiment 100 of the present invention is provided, which includes a camera module 101, the image acquisition module 10, the image analysis module 20 and control module 30.

[0011]该摄像模块101用于拍摄一个当前车辆前方的全部物体,以得到一个第一当前帧影像。 [0011] The camera module 101 for photographing a current all objects ahead of the vehicle, to obtain a first image of the current frame. 在本实施例中,该摄像模块1I为一个摄像机。 In the present embodiment, the camera is a camera module 1I.

[0012]该影像获取模块10用于获取该第一当前帧影像。 [0012] The image acquisition module 10 for acquiring the first image of the current frame.

[0013]该影像分析模块20与该影像获取模块10电连接,用于对该第一当前帧影像进行曝光分析,以判断该第一当前帧影像曝光正常还是曝光不正常(即曝光过度或曝光不足,简称过曝或欠曝)。 [0013] The image analysis module 20 acquires the image module 10 is electrically connected to a first analysis of the exposure for the current image frame, to determine whether the current frame is the first image exposure is normal or not normal exposure (i.e., overexposure or insufficient, referred to as overexposed or underexposed). 若该第一当前帧影像曝光正常,则该影像分析模块20直接对该第一当前帧影像中的全部物体进行分析计算,以构建全部物体数据集。 If the first normal exposure of the current frame image, the image analysis module 20 directly to the entire object in a first image of the current frame analysis and calculation, in order to construct the entire object data set. 该全部物体数据集能够被用于行车安全预警的分析计算。 The entire set of data objects can be used to analyze the calculation of vehicle safety warning.

[0014]若该第一当前影像曝光不正常,则该影像分析模块20判断该第一当前帧影像属于整体曝光不正常还是部分区域曝光不正常。 [0014] If the first current is not normal exposure image, the image analysis module 20 determines that the first image of the current frame is normal or not belonging to overall exposure region exposed portion is not normal. 若该第一当前帧影像属于整体曝光不正常,则该影像分析模块20计算出该第一当前帧影像整体过曝或欠曝的程度。 If the first part of the current frame image is not normal global exposure, the image analysis module 20 first calculates the degree of the current frame image entirety of overexposed or underexposed. 若该第一当前帧影像属于部分区域曝光不正常,则该影像分析模块20计算出该第一当前帧影像中曝光不正常区域的过曝或欠曝的程度,并对该第一当前帧影像中曝光正常区域的物体进行分析计算,构建第一部分的物体数据集D1。 If the current frame is the first image sub-region is not normally exposed, the image analysis module 20 calculates the first image of the current frame is not the normal exposure region under or overexposed exposure of the degree, and the first image of the current frame normal exposure object area analysis and calculation build object data set D1 of the first portion. 在本实施例中,该影像分析模块20通过灰度或者直方图的方式对该第一当前帧影像中的所有点进行分析计算,以对该第一当前帧影像进行曝光分析。 In the present embodiment, the image analysis module 20 for analysis and calculation of the current frame for all points in the first image by histogram or gradation manner, the current frame to the first image exposure analysis.

[0015]该影像分析模块20还用于根据该第一当前帧影像整体或部分区域过曝或欠曝的程度发出控制信号给该控制模块30。 [0015] The image analysis module 20 is further configured to issue a control signal to the control module 30 according to the degree of the current frame is a first image region in whole or part of overexposed or underexposed. 该控制模块30与该影像分析模块20电连接,用于根据该影像分析模块20的控制信号对该摄像模块101的曝光参数进行调整。 The control module 30 is electrically connected to the image analysis module 20, for adjusting the exposure parameters of a camera module 101 according to a control signal of the image analysis module 20.

[0016]具体的,(I)若该第一当前帧影像整体过曝,则该控制模块30调整该摄像模块101的光圈和曝光时间等曝光参数,以降低进光量;(2)若该第一当前帧影像整体欠曝,则该控制模块30调整该摄像模块101的光圈和曝光时间等曝光参数,以提高进光量;(3)若该第一当前帧影像中的部分区域过曝,则该控制模块30调整该摄像模块101的光圈和曝光时间等曝光参数,以降低进光量,这样会造成之前过曝的区域曝光正常,而之前正常曝光的区域则曝光不足;(4)若该第一当前帧影像中的部分区域欠曝,则该控制模块30调整该摄像模块101的光圈和曝光时间等曝光参数,以提高进光量,这样会造成之前欠曝的区域曝光正常,而之前正常曝光的区域则曝光过度。 [0016] Specifically, (the I) if the first current frame image overall overexposure, the control module 30 to adjust the imaging module aperture and exposure time of the exposure parameters 101 to reduce the amount of light; (2) if the second a current frame image overall due to exposure, the control module 30 to adjust the aperture and exposure time of an exposure parameter of the imaging module 101 to increase the amount of light; (3) if the first current part of a frame image is overexposed, then the control module 30 adjusts the camera module aperture and exposure time of the exposure parameters 101 to reduce the amount of light, this will cause the region overexposed prior to exposure of normal, but before the normal exposure region is less than the exposure; (4) if the second a current part of a frame image is underexposed, the control module 30 to adjust the aperture and exposure time of an exposure parameter of the imaging module 101 to increase the amount of light, the less area of ​​exposure exposed to normal prior to such cause, and before the normal exposure overexposed areas.

[0017]该摄像模块101根据该控制模块30调整后的曝光参数再次拍摄该当前车辆前方的全部物体,以得到第二当前帧影像。 [0017] The exposure of the camera module 101 to adjust the parameters of the control module 30 photograph the entire object is currently ahead of the vehicle again to obtain a second image of the current frame.

[0018]该影像获取模块10还用于获取该第二当前帧影像。 [0018] The image capturing module 10 is further configured to obtain the second image of the current frame.

[0019]具体的,对于整体曝光不正常的第一当前帧影像,调整曝光参数后,该第二当前帧影像整体曝光正常;对于部分区域曝光不正常的第一当前帧影像,调整曝光参数后,该第一当前帧影像中曝光不正常的区域在第二当前帧影像中变成曝光正常区域,该第一当前帧影像中曝光正常的区域在第二当前帧影像中变成曝光不正常的区域。 After exposure to the partial region of the first abnormal current frame image, adjust the exposure parameters; [0019] Specifically, the overall exposure of the first abnormal current frame image after adjusting the exposure parameters, the second image of the current frame normal global exposure the first abnormal current exposure region of the frame image into a normal exposure region in a second image of the current frame, the current frame is the first normal image exposure in the second exposure area becomes the current image frame is not normal area.

[0020]该影像分析模块20还用于对该第二当前帧影像进行曝光分析,以判断该第二当前帧影像是整体曝光正常还是部分区域曝光正常。 [0020] The image analysis module 20 is also used for the current frame, a second image exposure analysis, to determine whether the second image of the current frame is an integral part of the exposure region exposed normal or normal. 该影像分析模块20还用于构建全部物体数据集。 The image analysis module 20 is further configured to construct all object data sets.

[0021]具体的,若该第二当前帧影像是整体曝光正常,则该影像分析模块20对该第二当前帧影像中的全部物体进行分析计算,以构建全部物体数据集。 [0021] Specifically, if the current frame image is the second normal global exposure, the image analysis module 20 of the second current-frame image analysis and calculation of all the objects, to construct the entire object data set. 该全部物体数据集能够被用于行车安全预警的分析计算。 The entire set of data objects can be used to analyze the calculation of vehicle safety warning.

[0022]若该第二当前帧影像是部分区域曝光正常,则该影像分析模块20对该第二当前帧影像中曝光正常的区域中的物体进行分析计算,构建第二部分的物体数据集D2,然后采用将该第一部分的物体数据集Dl与该第二部分的物体数据集D2相加,S卩D1+D2的方式得到全部物体数据集。 [0022] If the second partial region of the current frame image is properly exposed, the image analysis module 20 of the second current image frame exposure area of ​​the normal object analysis and calculation build object data sets D2 of the second portion and using the object data sets Dl and D2 of the object data set by adding the second portion of the first portion, S Jie D1 + D2 manner to give all of the object data set. 该全部物体数据集能够被用于行车安全预警的分析计算。 The entire set of data objects can be used to analyze the calculation of vehicle safety warning.

[0023]如图2及图3所示,本发明较佳实施例所提供的一种提高影像中物体识别的方法,其包括如下步骤: [0023] As shown in FIG. 2 and FIG. 3, a method for improving the image object recognition according to the preferred embodiment of the present invention is provided, comprising the steps of:

[0024] SO:利用一个摄像模块(比如摄像机)拍摄一个当前车辆前方的全部物体,以得到一个第一当前帧影像。 [0024] SO: using a camera module (for example, a camera) photographing an entire object in front of the present vehicle, to obtain a first image of the current frame.

[0025] S1:获取该第一当前帧影像。 [0025] S1: first acquiring the current image frame.

[0026] S2:对该第一当前帧影像进行曝光分析,以判断该第一当前帧影像曝光正常还是曝光不正常(即曝光过度或曝光不足,简称过曝或欠曝)。 [0026] S2: a current frame of the first image exposure analysis, to determine whether the current frame is the first image exposure is normal or not normal exposure (i.e., overexposed or underexposed, overexposed or underexposed referred to).

[0027] S3:若该第一当前帧影像曝光正常,则对该第一当前帧影像中的全部物体进行分析计算,以构建全部物体数据集,该全部物体数据集能够被用于行车安全预警的分析计算。 [0027] S3: When the current frame is the first image exposure is normal, all the first object in the current frame image analysis and calculation, in order to construct the entire object data set, the entire set of data objects can be used for road safety warning analysis and calculation.

[0028] S4:若该第一当前帧影像曝光不正常,则判断该第一当前帧影像属于整体曝光不正常还是部分区域曝光不正常。 [0028] S4: If the current frame is the first image exposure is not normal, it is determined that the current frame is the first image does not belong to the normal global exposure region or a partial exposure is not normal.

[0029] S5:若该第一当前帧影像属于整体曝光不正常,则计算出该第一当前帧影像整体过曝或欠曝的程度。 [0029] S5: If the current frame is the first image belonging to overall exposure is not normal, the calculated first degree of the current frame image entirety of overexposed or underexposed.

[0030] S6:根据该第一当前帧影像整体过曝或欠曝的程度调整该摄像模块的曝光参数,控制该摄像模块再次拍照,得到一个第二当前帧影像,然后转入步骤S9。 [0030] S6: The exposure parameter of the first image of the current frame under the overall overexposed or adjusting the degree of exposure of the camera module, the camera module photographing control again to obtain a second image of the current frame, and then proceeds to step S9.

[0031] S7:若该第一当前帧影像属于部分区域曝光不正常,则计算出该第一当前帧影像中的曝光不正常区域过曝或欠曝的程度,并对该第一当前帧影像中曝光正常区域的物体进行分析计算,构建第一部分的物体数据集Dl。 [0031] S7: If the first sub-region of the current frame image exposure is not normal, then the current frame is calculated by the first image exposure area is not overexposed or under normal degree of exposure, and the first frame of the current image normal exposure object area analysis and calculation, the first build object data set Dl portion.

[0032] S8:根据该第一当前帧影像中曝光不正常区域过曝或欠曝的程度调整该摄像模块的曝光参数,控制该摄像模块再次拍摄该当前车辆前方的全部物体,得到一个第二当前帧影像,然后转入步骤S9。 [0032] S8: through the current exposure according to the first region of the frame image is not normal exposure or under exposure parameter to adjust the degree of exposure of the camera module, the camera module controls the entire photographing the object in front of the current vehicle again to give a second the current frame image, and then proceeds to step S9.

[0033] S9:从该摄像模块中获取该第二当前帧影像。 [0033] S9: Gets the current frame image from the second camera module.

[0034] S10:对该第二当前帧影像进行曝光分析,以判断该第二当前帧影像属于整体曝光正常还是部分区域曝光正常。 [0034] S10: the second current image frame exposure analysis, to determine whether the image belongs to a second overall exposure of the current frame is normal or normal exposure region portion.

[0035] Sll:若该第二当前帧影像属于整体曝光正常,则对该第二当前帧影像中的全部物体进行分析计算,以构建全部物体数据集,该全部物体数据集能够被用于行车安全预警的分析计算。 [0035] Sll: if the second image of the current frame belongs to the normal global exposure, the whole of the second object in the current frame image analysis and calculation, in order to construct the entire object data set, the entire set of data objects can be used for driving analysis of safety warning calculations.

[0036] S12:若该第二当前帧影像是部分区域曝光正常,则对该第二当前帧影像中曝光正常的区域中的物体进行分析计算,构建第二部分的物体数据集D2。 [0036] S12: If the current frame image is the second part of the normal exposure region, the normal exposure current for the second frame image in the region of the object analysis and calculation build object data sets D2 of the second portion.

[0037] S13:采用将该第一部分的物体数据集Dl与该第二部分的物体数据集D2相加,SPDl+D2的方式构建全部物体数据集,该全部物体数据集能够被用于行车安全预警的分析计算。 [0037] S13: using the first portion of the object data sets Dl and D2 of the object data set is added to the second portion, the entire build object data sets SPDl + D2 manner, all of the object data set can be used for road safety analysis of early warning calculations.

[0038]与现有技术相比较,本发明的提高影像中物体识别的系统及方法,能够有效识别当前车辆前方的全部物体,以更好地对驾驶者进行保护。 [0038] Compared with the prior art, an object recognition system and method of the present invention improve the image, it is possible to identify all currently active object in front of the vehicle, in order to better protect the driver.

[0039]以上所述仅为本发明的较佳实施例而已,并不用以限制本发明,凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等,均应包含在本发明的保护范围之内。 [0039] The foregoing is only preferred embodiments of the present invention but are not intended to limit the present invention, any modifications within the spirit and principle of the present invention, equivalent substitutions and improvements should be included in the present within the scope of the invention.

Claims (10)

  1. 1.一种提高影像中物体识别的系统,其包括摄像模块、影像获取模块、影像分析模块及控制模块,该摄像模块用于拍摄一个当前车辆前方的全部物体,以得到一个第一当前帧影像;该影像获取模块用于获取该第一当前帧影像,该影像分析模块用于对该第一当前帧影像进行曝光分析,若该第一当前帧影像属于整体曝光不正常,则计算出该第一当前帧影像过曝或欠曝的程度;该控制模块根据该第一当前帧影像过曝或欠曝的程度调整该摄像模块的曝光参数;该摄像模块根据调整后的曝光参数再次拍摄该当前车辆前方的全部物体,以得到第二当前帧影像;该影像获取模块用于获取该第二当前帧影像;该影像分析模块还用于对该第二当前帧影像进行曝光分析,若该第二当前帧影像整体曝光正常,则对该第二当前帧影像中的全部物体进行分析计算,以构建全部物体数据 1. A method of increasing image object recognition system, which includes a camera module, the image acquisition module, the image analysis module and a control module, the imaging means for imaging the entire object in front of a present vehicle, to obtain a first image of the current frame ; obtaining module configured to obtain the image of the current frame is the first image, the image analysis module for performing analysis of the exposure of the first image of the current frame, if the current frame is the first image belonging to overall exposure is not normal, the calculated the first a current image frame over exposure or under-exposed extent of; the control module of the first current image frame over exposure or under exposure parameter to adjust the degree of exposure of the imaging module according to; the imaging module in accordance with the adjusted exposure parameter the current shooting again all objects in front of the vehicle, to obtain a second image of the current frame; obtaining module configured to obtain the image of the second image of the current frame; the image analysis module is further used for the current frame, a second image exposure analysis, if the second overall exposing the image of the current frame is normal, all the objects in the second image of the current frame analysis and calculation, in order to construct the entire object data 集;该全部物体数据集能够被用于行车安全预警的分析计算。 Set; the entire set of data objects can be used to analyze the calculation of vehicle safety warning.
  2. 2.如权利要求1所述的提高影像中物体识别的系统,其特征在于,若该第一当前帧影像整体过曝,则该控制模块调整该摄像模块的曝光参数,以降低进光量,使该第二当前帧影像变成整体曝光正常;若该第一当前帧影像整体欠曝,则该控制模块调整该摄像模块的曝光参数,以提高进光量,使该第二当前帧影像变成整体曝光正常。 2. improve the image of the object recognition system 1 as claimed in claim wherein, if the first overall current frame image is overexposed, the exposure control module to adjust the parameters of the camera module to reduce the amount of light, so that the second current frame image into normal global exposure; if the first frame of the current image under exposure overall, the control module to adjust the exposure parameters of the camera module, to increase the amount of light, so that the second image of the current frame become an integral exposure to normal.
  3. 3.如权利要求1所述的提高影像中物体识别的系统,其特征在于,若该第一当前帧影像属于部分区域曝光不正常,则该影像分析模块还对该第一当前帧影像中曝光正常区域的物体进行分析计算,构建第一部分的物体数据集;若该第二当前帧影像属于部分区域曝光正常,则该影像分析模块还对该第二当前帧影像中曝光正常的区域中的物体进行分析计算,构建第二部分的物体数据集;该影像分析模块采用将第一部分的物体数据集与第二部分的物体数据集相加的方式得到全部物体数据集。 3. The increase in video according to an object recognition system as claimed in claim, wherein, if the first sub-region of the current frame image exposure is not normal, the image analysis module further exposing the first current image frame an object analysis and calculation of the normal region, a first set of object data constructing section; second region if the current frame image sub-region exposed normally, the normal exposure image analysis module is further on the second image in the current frame object analysis and calculation, the object data sets to build the second portion; the image analysis module uses the object data set of the object data set of the first portion and the second portion of the object all the way to get the sum of the data set.
  4. 4.如权利要求3所述的提高影像中物体识别的系统,其特征在于,若该第一当前帧影像中的部分区域过曝,则该控制模块调整该摄像模块的曝光参数,以降低进光量,使得该第一当前帧图像中过曝的区域在该第二当前帧图像中曝光正常,该第一当前帧图像中曝光正常的区域在该第二当前帧图像中曝光不足;若该第一当前帧影像中的部分区域欠曝,则该控制模块调整该摄像模块光参数,以提高进光量,使得该第一当前帧图像中欠曝的区域在该第二当前帧图像中曝光正常,该第一当前帧图像中曝光正常的区域在该第二当前帧图像中曝光过度。 4. improve the image of the object 3 in the identification system according to claim, wherein, if the first frame of the current partial area of ​​the image is overexposed, the exposure control module to adjust the parameters of the camera module to reduce the feed the amount of light, such that a first region of the current frame image is overexposed normal exposure frame image in the second current, the first current normal exposure region of the frame image in the underexposed second current image; if the second a partial region of the current frame image is underexposed, the control module adjusts parameters of the optical imaging module to increase the amount of light, such that a first region of the current frame image under exposure of the normal exposure frame image in the second current, the first over-current normal exposure frame image in the exposed areas of the second current image.
  5. 5.如权利要求1所述的提高影像中物体识别的系统,其特征在于,该影像分析模块通过灰度或者直方图的方式对该第一当前帧影像中的所有点进行分析计算,以对该第一当前帧影像进行曝光分析。 5. The improved image of the object recognition system of claim 1, wherein the image analysis module Analysis calculated for all points of the current frame of the first image through the grayscale histogram or manner, in order to the first analysis of the current frame image is exposed.
  6. 6.如权利要求1所述的提高影像中物体识别的系统,其特征在于,若该第一当前帧影像曝光正常,则该影像分析模块直接对该第一当前帧影像中的全部物体进行分析计算,以构建全部物体数据集,该全部物体数据集能够被用于行车安全预警的分析计算。 6. improve the image of the object recognition system 1 as claimed in claim wherein, if the first normal exposure of the current frame image, the image analysis module all of the first object image in the current frame directly analyzed computing, to build the entire data set of the object, all object data sets which can be used for analysis and calculation of road safety warning.
  7. 7.—种提高影像中物体识别的方法,其包括如下步骤:使用一个摄像模块拍摄一个当前车辆前方的全部物体,以得到一个第一当前帧影像;获取该第一当前帧影像;对该第一当前帧影像进行曝光分析;若该第一当前帧影像属于整体曝光不正常,则计算出该第一当前帧影像整体过曝或欠曝的程度;根据该第一当前帧影像整体过曝或欠曝的程度调整该摄像模块的曝光参数;该摄像模块根据调整后的曝光参数再次拍摄该当前车辆前方的全部物体,获取一个第二当前帧影像;对该第二当前帧影像进行曝光分析;若该第二当前帧影像属于整体曝光正常,则对该第二当前帧影像中的全部物体进行分析计算,以构建全部物体数据集,该全部物体数据集能够被用于行车安全预警的分析计算。 7.- method to improve image object recognition, comprising the steps of: using a camera module capturing a full current object ahead of the vehicle, to obtain a first image of the current frame; a first obtaining the current video frame; the first exposing a current frame image analysis; if the first frame of the current image belongs overall exposure is not normal, the calculated first degree of the current frame image entirety of overexposed or underexposed; overexposed or overall current frame based on the first image the degree of exposure under the adjusted exposure parameter of the imaging module; exposure of the imaging module in accordance with the adjusted parameters to shoot again all the current object in front of the vehicle, obtaining a second image of the current frame; a second current frame of the image exposure analysis; If the second image of the current frame belongs to the normal global exposure, the whole of the second object in the current frame image analysis and calculation, in order to construct the entire object data set, the entire set of data objects can be used for traffic safety warning analysis calculated .
  8. 8.如权利要求7所述的提高影像中物体识别的方法,其特征在于,在步骤“对该第一当前帧影像进行曝光分析”后还包括步骤“若该第一当前帧影像属于部分区域曝光不正常,则计算出该第一当前帧影像中曝光不正常区域过曝或欠曝的程度,并对该第一当前帧影像中曝光正常区域的物体进行分析计算,构建第一部分的物体数据集;根据该第一当前帧影像中曝光不正常区域过曝或欠曝的程度调整该摄像模块的曝光参数;该摄像模块根据调整后的曝光参数再次拍摄该当前车辆前方的全部物体,获取一个第二当前帧影像;对该第二当前帧影像进行曝光分析;若该第二当前帧影像属于部分区域曝光正常,则对该第二当前帧影像中曝光正常的区域中的物体进行分析计算,构建第二部分的物体数据集;采用将第一部分的物体数据集与该第二部分的物体数据集相加的方式 8. The improved method of claim 7 image object recognition claim, characterized in that the "current frame of the first image exposure analysis" further comprises the step after step "portion of the first region if a current frame image belongs exposure is not normal, the calculated current exposure of the first image frame is not a normal region under or overexposed degree of exposure, and the exposure of the first object in the current frame image analysis and calculation of the normal region, a first portion of the object data constructed set; through current exposure according to the first region of the frame is not normal or under-exposed image exposure to adjust the degree of exposure parameter of the imaging module; exposure of the imaging module in accordance with the adjusted parameters of the photographed object in front of all the current vehicle again, obtaining a a second image of the current frame; a second current frame of the image exposure analysis; current frame if the second portion of the image belongs to the normal exposure region, the exposure of the second current image frame of a normal object region analysis and calculation, Construction of the second portion of the object data set; object data set using the object data sets of the first portion and the second portion of the additive manner 到全部物体数据集,该全部物体数据集能够被用于行车安全预警的分析计算”。 All the object data set, the entire set of data objects can be used to calculate the traffic safety warning analysis. "
  9. 9.如权利要求7所述的提高影像中物体识别的方法,其特征在于,在步骤“对该第一当前帧影像进行曝光分析”后还包括步骤“若该第一当前帧影像曝光正常,则直接对该第一当前帧影像中的全部物体进行分析计算,以构建全部物体数据集,该全部物体数据集能够被用于行车安全预警的分析计算。 9. The improved method of object recognition in an image according to claim 7, characterized in that the "current frame of the first image exposure analysis" step further comprises the step "If the first normal exposure of the current frame image, all of the first object directly to the current frame of image analysis and calculation, in order to construct the entire object data set, the entire set of data objects can be used to analyze the calculation of vehicle safety warning.
  10. 10.如权利要求7所述的提高影像中物体识别的方法,其特征在于,在步骤“对该第一当前帧影像进行曝光分析”及步骤“对该第二当前帧影像进行曝光分析”中通过灰度或者直方图的方式对该第一当前帧影像及该第二当前帧影像中的所有点进行分析计算,以对该第一当前帧影像及该第二当前帧影像进行曝光分析。 10. improve the image of the object recognition method in 7 claim, wherein "a current frame of the first image exposure analysis" of steps and "a current frame of the second analysis image exposure" analysis calculated for the current frame of the first image and the second image at all points in the current frame by way of a histogram or gradation to the current frame of the first image and the second image of the current frame exposure analysis.
CN 201610066335 2016-01-29 2016-01-29 System and method for improving object identification in image CN105744156A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 201610066335 CN105744156A (en) 2016-01-29 2016-01-29 System and method for improving object identification in image

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN 201610066335 CN105744156A (en) 2016-01-29 2016-01-29 System and method for improving object identification in image

Publications (1)

Publication Number Publication Date
CN105744156A true true CN105744156A (en) 2016-07-06

Family

ID=56247083

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201610066335 CN105744156A (en) 2016-01-29 2016-01-29 System and method for improving object identification in image

Country Status (1)

Country Link
CN (1) CN105744156A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030206241A1 (en) * 1997-11-21 2003-11-06 Matsushita Electric Industrial Co., Ltd. Imaging apparatus with dynamic range expanded, a video camera including the same, and a method of generating a dynamic range expanded video signal
CN101119439A (en) * 2007-08-22 2008-02-06 东风汽车有限公司 Autocontrol method of vehicle mounted camera shooting clear carriageway image
CN101483721A (en) * 2008-01-08 2009-07-15 华晶科技股份有限公司 Video processing method and video capturing apparatus applying the method
CN101646021A (en) * 2008-08-08 2010-02-10 株式会社电装 Exposure determining device and image processing apparatus

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030206241A1 (en) * 1997-11-21 2003-11-06 Matsushita Electric Industrial Co., Ltd. Imaging apparatus with dynamic range expanded, a video camera including the same, and a method of generating a dynamic range expanded video signal
CN101119439A (en) * 2007-08-22 2008-02-06 东风汽车有限公司 Autocontrol method of vehicle mounted camera shooting clear carriageway image
CN101483721A (en) * 2008-01-08 2009-07-15 华晶科技股份有限公司 Video processing method and video capturing apparatus applying the method
CN101646021A (en) * 2008-08-08 2010-02-10 株式会社电装 Exposure determining device and image processing apparatus

Similar Documents

Publication Publication Date Title
US20060215882A1 (en) Image processing apparatus and method, recording medium, and program
US20110058050A1 (en) Method and apparatus for motion blur and ghosting prevention in imaging system
US20080181597A1 (en) Photographing apparatus, method for controlling photographing apparatus and computer-readable recording medium containing program
CN103021177A (en) Method and system for processing traffic monitoring video image in foggy day
JP2007096510A (en) Front photographing apparatus
CN1499823A (en) camera
US20080024606A1 (en) Image processing apparatus
US20150086077A1 (en) System and method of alerting a driver that visual perception of pedestrian may be difficult
JP2005073296A (en) Exposure control apparatus for on-vehicle camera
JP2002247361A (en) Image processor, image processing method and recording medium having recorded programs for executing the same
CN101344988A (en) Image acquisition and processing equipment and method, vehicle monitoring and recording system
CN101893804A (en) Exposure control method and device
US20140307129A1 (en) System and method for lens shading compensation
CN101304489A (en) Automatic exposure method and apparatus
JPH09282452A (en) Monitor
JP2008287091A (en) Device and method for automatic focusing, and device and method for taking image
JP2002145072A (en) Railroad crossing obstacle detecting device
CN102568242A (en) Signal lamp state detection method and system based on video processing
JP2006270218A (en) Electronic camera and electronic camera system
Ngo et al. A visibility improvement system for low vision drivers by nonlinear enhancement of fused visible and infrared video
JP2010272067A (en) Image processing apparatus
US20090015683A1 (en) Image processing apparatus, method and program, and recording medium
US20110221906A1 (en) Multiple Camera System for Automated Surface Distress Measurement
US20120300074A1 (en) Detection apparatus and detection method
US20090147080A1 (en) Apparatus for detecting feature of driver's face

Legal Events

Date Code Title Description
C06 Publication
C10 Entry into substantive examination