Recent Patents in Signal Processing (August 2016) – Pedestrian Detection

For our August 2016 issue, we cover recent patents granted in the area of pedestrian detection using various signal processing approaches. The topic represents a central issue in up-to-date research on self driving vehicles, surveillance and city monitoring.

In patent no. 9,352,715 a vehicle bumper including a pedestrian collision detection apparatus includes: a chamber member, a pressure detector, a collision determination unit, an absorber, and a bumper cover. The chamber member is disposed in a vehicle width direction as a longitudinal direction thereof and is adjacent to an outer side surface of a bumper reinforcement in a vehicle front-rear direction, the bumper reinforcement is disposed in the vehicle width direction as a longitudinal direction thereof and inside of the chamber member functions as a pressure chamber. The pressure detector outputs a signal corresponding to a change in pressure of the pressure chamber. The bumper cover is provided on the outside of the chamber member and the absorber in the vehicle front-rear direction and includes a projected portion projected from an opposite wall that faces the chamber member to the chamber member side.

Patent no. 9,165,463 describes a technology by which ambient data related to a vehicle is sensed and processed, for use in determining a state change related to external traffic awareness. Based upon the state change, an allowed level of interactivity with a user interface may be changed, and/or a notification may be output. Images and/or depth data may be sensed as part of determining whether a user who is interacting with a device in a stopped vehicle is to be made aware of the changed condition with respect to other vehicles, pedestrians and/or the like.

A pedestrian detection system is presented in patent no. 9,152,856 for detecting whether there is a pedestrian in a scene, the pedestrian detection system includes an image-capturing module, a preprocessing module, a human detection module, an image-stitching module and a decision module. The image-capturing module is configured for generating a plurality of first detection image data according to a contrast decision result. The preprocessing module is configured for generating a plurality of first image skeleton data according to the first detection image data. The human detection module is configured for generating a plurality of second image skeleton data. The image-stitching module is configured for stitching the plurality of first detection image data to generate at least one third detection image data. The decision module is configured for generating and outputting a detection result according to the third detection image data. A pedestrian detection method is disclosed herein as well.

Following the invention no. 9,087,263, a vision based pedestrian and cyclist detection method includes receiving an input image, calculating a pixel value difference between each pixel and the neighbor pixels thereof, quantifying the pixel value difference as a weight of pixel, proceeding statistics for the pixel value differences and the weights, determining intersections of the statistics as a feature of the input image, classifying the feature into human feature and non-human feature, confirming the human feature belonging to cyclist according to the spatial relationship between the human feature and the detected two-wheeled vehicle, and retaining one detection result for each cyclist by suppressing other weaker spatial relationships between the human feature and the detected two-wheeled vehicle.

In patent no. 9,064,157 A pedestrian detection system and method includes: dividing an image to a plurality of granules, and counting magnitude difference value of each granule in diagonal orientation to obtain features of HOGG. And the HOGG and the HOG captured can work together to improve the detection rate and reduce the false alarm rate, which is the ultimate goal of the vision based pedestrian detection.

In patent no. 9,008,365 system, apparatus, and method embodiments are provided for detecting the presence of a pedestrian in an image. In an embodiment, a method for determining whether a person is present in an image includes receiving a plurality of images, wherein each image comprises a plurality of pixels and determining a modified center symmetric local binary pattern (MS-LBP) for the plurality of pixels for each image, wherein the MS-LBP is calculated on a gradient magnitude map without using an interpolation process, and wherein a value for each pixel is a gradient magnitude.

A pedestrian collision detection device is obtained in patent no 8,864,196 that is capable of improving pedestrian detection performance in the vicinity of a bumper corner portion. A pedestrian collision detection device includes a chamber member disposed with pressure detectors, and an ECU is connected to the pressure detectors. Terminal portions of the chamber member are wrapped around so as to cover vehicle width direction outside end faces of bumper reinforcement at bumper corner portion sides. When a load of a specific value or greater is input to the terminal portions of the chamber member from a bumper cover side during a collision, the terminal portions obtain a reactive force from the bumper reinforcement and undergo compression deformation towards the vehicle width direction inside, and the pressure inside a pressure chamber of the chamber member changes

In patent no. 8,861,842 a computer implemented method for detecting the presence of one or more pedestrians in the vicinity of the vehicle is disclosed. Imagery of a scene is received from at least one image capturing device. A depth map is derived from the imagery. A plurality of pedestrian candidate regions of interest (ROIs) is detected from the depth map by matching each of the plurality of ROIs with a 3D human shape model. At least a portion of the candidate ROIs is classified by employing a cascade of classifiers tuned for a plurality of depth bands and trained on a filtered representation of data within the portion of candidate ROIs to determine whether at least one pedestrian is proximal to the vehicle.

If you have an interesting patent to share when we next feature patents related to pedestrian detections, or if you are especially interested in a signal processing research field that you would like to highlight in this section, please send email to Csaba Benedek (benedek.csaba AT sztaki DOT mta DOT hu).

References

Number: 9,352,715
Title: Vehicle bumper including pedestrian collision detection apparatus
Inventors: Narita; Sotaro (Toyota, JP), Matsunaga; Youichi (Kariya, JP), Goda; Naoki (Kariya, JP)
Issued:  May 31, 2016
Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota, JP)

Number: 9,165,463
Title: Ambient vehicle and pedestrian state detection for device notification
Inventors: Paek; Timothy S. (Sammamish, WA), Bahl; Paramvir (Bellevue, WA)
Issued:  October 20, 2015
Assignee: Microsoft Technology Licensing, LLC (Redmond, WA)

Number: 9,152,856
Title: Pedestrian detection system and method
Inventors: Tsai; Augustine (Taipei, TW), Tsai; Jui-Yang (Tainan, TW)
Issued:  October 6, 2015
Assignee: Institute For Information Industry (Taipei, TW)

Number: 9,087,263
Title: Vision based pedestrian and cyclist detection method
Inventors: Fu; Li-Chen (Taipei, TW), Hsiao; Pei-Yung (Taipei, TW), Chan; Yi-Ming (Taipei, TW), Lo; Min-Fang (Zhongli, TW)
Issued:  June 23, 2015
Assignee:        National Chung Shan Institute Of Science And Technology (Taoyuan, TW)

Number: 9,064,157
Title: Pedestrian detection systems and methods
Inventors: Fu; Li-Chen (Taoyuan County, TW), Hsiao; Pei-Yung (Taoyuan County, TW), Wu; Cheng-En (Taoyuan County, TW), Chan; Yi-Ming (Taoyuan County, TW), Hu; Shao-Chung (Taoyuan County, TW)
Issued:  July 21, 2015
Assignee: National Chung Shan Institute Of Science And Technology (Taoyuan, TW)

Number: 9,008,365
Title: Systems and methods for pedestrian detection in images
Inventors: Xu; Jingsong (Kingsford, AU), Ni; Zefeng (South Hurstville, AU), Wu; Qiang (Ashfield, AU), Zhang; Jian (Kensington, AU), Liu; Haibo (Shenzhen, CN), Zhang; Chen-Xiong (Plano, TX), Chen; Wei (Shenzhen, CN)
Issued:  April 14, 2015
Assignee: Huawei Technologies Co., Ltd. (Shenzhen, CN)

Number: 8,864,196
Title: Pedestrian collision detection device
Inventors: Shamoto; Takehisa (Toyota, JP)
Issued:  October 21, 2014
Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota, JP)

Number: 8,861,842
Title: Method and apparatus for real-time pedestrian detection for urban driving
Inventors: Jung; Sang-Hack (Jersey City, NJ), Bansal; Mayank (Plainsboro, NJ), Matei; Bogdan Calin Mihai (Princeton Junction, NJ), Eledath; Jayan (Princeton, NJ), Sawhney; Harpreet Singh (West Windsor, NJ), Kumar; Rakesh (West Windsor, NJ), Hadsell; Raia (Princeton Junction, NJ)
Issued:  October 14, 2014
Assignee:  SRI International (Menlo Park, CA)