# US 10,872,247 B2 · Image feature emphasis device, road surface feature analysis device, image feature emphasis method, and road surface feature analysis method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,872,247 B2 - Document ID: US10872247B2 - Status: Granted - Kind: B2 - Application number: 16/165,200 - Filed: 2018-10-19 - Published: 2019-05-30 - Granted: 2020-12-22 - Earliest claimed: 2017-11-28 - Assignees: Kabushiki Kaisha Toshiba; Toshiba Infrastructure Systems & Solutions Corporation - Applicants: Kabushiki Kaisha Toshiba; Toshiba Infrastructure Systems & Solutions Corporation - Inventors: Yoko Yonekawa; Yuuichi Nakamura; Nobuyuki Kumakura; Masaki Shiratsuki; Takahiko Yamazaki - Web page: https://patentgrep.com/patent/US10872247B2 ## CPC - G06T 5/94: based on local image properties, e.g. for local contrast enhancement - G06T 5/20: using local operators - G06T 7/0004: {Industrial image inspection} - G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80) - G06V 10/60: relating to illumination properties, e.g. using a reflectance or lighting model - G06V 20/588: {Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road} - G06T 2207/20021: Dividing image into blocks, subimages or windows - G06T 2207/20032: Median filtering - G06T 2207/30132: Masonry; Concrete - G06T 2207/30242: Counting objects in image - G06T 2207/30256: Lane; Road marking - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract According to one embodiment, an image feature emphasis device, a road surface feature analysis device, an image feature emphasis method, and a road surface feature analysis method which can improve the accuracy of detection of features of a road surface in a road surface image are provided. The image feature emphasis device includes a region acquirer and an image feature emphasis processor. The region acquirer acquires a region of a road surface portion from an image that has been captured. The image feature emphasis processor emphasizes a feature of the acquired region of the road surface portion by changing brightness values in the region of the road surface portion on the basis of a maximum brightness value and a minimum brightness value in the region of the road surface portion. ## Claims ### Claim 1 An image feature emphasis device comprising: an image input unit configured to input a road surface image in which a road surface is imaged; an image data storage configured to store the road surface image input by the image input unit; a road surface region extraction unit configured to identify an object imaged in the road surface image stored in the image data storage and to acquire a region, in which a pixel value of a pixel around the identified object is similar to the pixel value of the road surface, as a road surface region; an image feature emphasis processor configured to emphasize a feature of the acquired road surface region by changing brightness values in the road surface region on the basis of a maximum brightness value and a minimum brightness value in the road surface region; and an image output unit configured to output an emphasized image in which the characteristics of the road surface region are emphasized by the image feature emphasis processor. ### Claim 2 (depends on 1) The image feature emphasis device according to claim 1, wherein the image feature emphasis processor is configured to set a plurality of detection windows for the road surface region, calculate respective maximum and minimum brightness values of the detection windows, calculate a maximum representative brightness value and a minimum representative brightness value of all the detection windows using the calculated maximum and minimum brightness values, and emphasize a feature of the road surface region by changing brightness values in the road surface region on the basis of the calculated maximum and minimum representative brightness values. ### Claim 3 (depends on 2) The image feature emphasis device according to claim 2, wherein the image feature emphasis processor is configured to calculate, when a detection window in which a representative brightness value is an outlier is present among all the detection windows, a maximum representative brightness value and a minimum representative brightness value using brightness values in at least one of the detection windows excluding the detection window having the outlier. ### Claim 4 (depends on 2) The image feature emphasis device according to claim 2, wherein the image feature emphasis processor is configured to calculate, when road surface images are continuously input, a maximum representative brightness value and a minimum representative brightness value using brightness values in at least one of the detection windows excluding a detection window in which a change in a representative brightness value is equal to or greater than a threshold value. ### Claim 5 A road surface feature analysis device comprising: an image input unit configured to input a road surface image in which a road surface is imaged; an image data storage configured to store the road surface image input by the image input unit; a road surface region extraction unit acquirer configured to identify an object imaged in the road surface image stored in the image data storage and to acquire a region, in which a pixel value of a pixel around the identified object is similar to the pixel value of the road surface, as a road surface region; an image feature emphasis processor configured to emphasize a feature of the acquired the road surface region by changing brightness values in the road surface region on the basis of a maximum brightness value and a minimum brightness value in the road surface region; a road surface feature detector configured to acquire an emphasized image in which the characteristics of the road surface region are emphasized by the image feature emphasis processor and detects deterioration of the road surface by image processing from road surface region in the acquired emphasized image; and an inspection result output unit configured to output an inspection result according to the deterioration of the road surface detected by the road surface feature detector. ### Claim 6 (depends on 5) The road surface feature analysis device according to claim 5, wherein the road surface feature detector is configured to detect a pavement crack of a road surface from the road surface region within the emphasized image, in which a feature of the road surface region is emphasized, through image processing. ### Claim 7 An image feature emphasis method comprising: an image input process including inputting a road surface image in which a road surface is imaged; an image data recording process including recording the road surface image input by the image input process an image data storage; a road surface region extraction process including identifying an object imaged in the road surface image stored in the image data storage and to acquire a region, in which a pixel value of a pixel around the identified object is similar to the pixel value of the road surface, as a road surface region; an image feature emphasis processing process including emphasizing a feature of the acquired road surface region by changing brightness values in the road surface region on the basis of a maximum brightness value and a minimum brightness value in the road surface region; and an image output process including outputting an emphasized image in which the characteristics of the road surface region are emphasized by the image feature emphasis processing process. ### Claim 8 (depends on 7) The image feature emphasis method according to claim 7, wherein the image feature emphasis processing process includes setting a plurality of detection windows for the road surface region, calculating respective maximum and minimum brightness values of the detection windows, calculating a maximum representative brightness value and a minimum representative brightness value of all the detection windows using the calculated maximum and minimum brightness values, and emphasizing a feature of the road surface region by changing brightness values in the road surface region on the basis of the calculated maximum and minimum representative brightness values. ### Claim 9 (depends on 8) The image feature emphasis method according to claim 8, wherein the image feature emphasis processing process includes calculating, when a detection window in which a representative brightness value is an outlier is present among all the detection windows, a maximum representative brightness value and a minimum representative brightness value using brightness values in at least one of the detection windows excluding the detection window having the outlier. ### Claim 10 (depends on 8) The image feature emphasis method according to claim 8, wherein the image feature emphasis processing process includes calculating, when road surface images are continuously input, a maximum representative brightness value and a minimum representative brightness value using brightness values in at least one of the detection windows excluding a detection window in which a change in a representative brightness value is equal to or greater than a threshold value. ### Claim 11 A road surface feature analysis method comprising: an image input process including inputting a road surface image in which a road surface is imaged; an image data recording process including recording the road surface image input by the image input process an image data storage; a road surface region extraction process including identifying an object imaged in the road surface image stored in the image data storage and to acquire a region, in which a pixel value of a pixel around the identified object is similar to the pixel value of the road surface, as a road surface region; an image feature emphasis processing process including emphasizing a feature of the acquired the road surface region by changing brightness values in the road surface region on the basis of a maximum brightness value and a minimum brightness value in the road surface region; a road surface feature detecting process including acquiring an emphasized image in which the characteristics of the road surface region are emphasized by the image feature emphasis processor and detects deterioration of the road surface by image processing from road surface region in the acquired emphasized image; and an inspection result output process including outputting an inspection result according to the deterioration of the road surface detected by the road surface feature detecting process. ### Claim 12 (depends on 11) The road surface feature analysis method according to claim 11, wherein the road surface feature detecting process includes detecting a pavement crack of a road surface from the road surface region within the emphasized image, in which a feature of the road surface region is emphasized, through image processing. ### Claim 13 (depends on 1) The image feature emphasis device according to claim 1, the road surface region extraction unit identifies moving objects from the road surface image and identifies a vertical direction from the positions of tires of the moving objects, and acquires a region, in which below the moving objects and whose pixel values are similar to the pixel value of the road surface registered in advance, as the road surface region. ### Claim 14 (depends on 1) The image feature emphasis device according to claim 1, further comprising: a setting display configured to set the road surface region, the road surface region extraction unit acquires a region specified by an user in the setting display, as the road surface region.