Abstract: Human lying posture detections are disclosed. A human lying on a bed is detected by obtaining an image through a depth camera, detecting objects in the image and marking the objects in the image using 2D bounding boxes by deep learning, determining the human being in a lying posture in response to a width and a height of the 2D bounding box of the human meeting a predetermined condition, detecting one or more skin areas in the image and generating skin area 2D bounding boxes to mark each of the one or more skin areas using a skin detection algorithm, and determining the human being in the lying posture in response to the skin area 2D bounding boxes and the 2D bounding box of the bed meeting a predetermined positional relationship.

Abstract: Navigation of a mobility aid robot having a camera and gripping part(s) disposed toward different directions is disclosed. The mobility aid robot is navigated to approach a user by identifying a posture of the user through the camera, determining a mode of the robot according to a type of the specified task to be performed on the user and the identified posture of the user, controlling the robot to move according to a planned trajectory corresponding to the determined mode of the robot, and turning the robot upon reaching the desired pose such that the gripping part faces the user, in response to the determined mode of the robot corresponding to the specified task of an assisting type and the user at one of a standing posture and a sitting posture.

Abstract: Carpet detection using an RGB-D camera and mobile machine movement control based thereon are disclosed. Carpets and carpet curls are detected by obtaining a RGB-D image pair including an RGB image and a depth image through an RGB-D camera, detecting carpet and carpet-curl areas in the RGB image and generating a 2D bounding box to mark each area using a deep learning model, and generating groups of carpet and carpet-curt points corresponding to each of the carpet and carpet-curl areas by matching each pixel of the RGB image within each 2D bounding box corresponding to the carpet and carpet curl areas to each pixel in the depth image.

Abstract: Response methods to human abnormal behaviors for a mobility aid robot having a user-facing camera are disclosed. The mobility aid robot responds to human abnormal behaviors by detecting a face of a human during the robot aiding the human to move through the camera, comparing an initial size of the face and an immediate size of the face in response to the face of the human having detected during the robot aiding the human to move, determining the human as in abnormal behavior(s) in response to the immediate size of the face being smaller than the initial size of the face, and performing response(s) corresponding to the abnormal behavior(s) in response to the human being in the abnormal behavior(s), where the response(s) include slowing down the robot.

Abstract: A human-object scene recognition method includes: acquiring an input RGB image and a depth image corresponding to the RGB image; detecting objects and humans in the RGB image using a segmentation classification algorithm based on a sample database; in response to detection of objects and/or humans, performing a segment detection to each of the detected objects and/or humans based on the ROB image and the depth image, and acquiring a result of the segment detection; calculating 3D hounding boxes for each of the detected objects and/or humans according to the result of the segment detection, and determining a position of each of the detected objects and/or humans according to the 3D bounding boxes.

Abstract: Human posture determination is disclosed. Human posture is determined by obtaining range image(s) through a range camera, detecting key points of an estimated skeleton of a human in color data of the range image(s) and calculating positions of the detected key points based on depth data of the range image(s), choosing a feature map from a set of predefined feature maps based on the detected key points among a set of predefined key points, obtaining two features of a body of the human corresponding to the chosen feature map based on the positions of the detected key points, and determining a posture of the human according to the two features in the chosen feature map.

Abstract: On-floor obstacle detection using an RGB-D camera is disclosed. An obstacle on a floor is detected by receiving an image including depth channel data and RGB channel data through the RGB-D camera, estimating a ground plane corresponding to the floor based on the depth channel data, obtaining a foreground of the image corresponding to the ground plane based on the depth channel data, performing a distribution modeling on the foreground of the image based on the RGB channel data to obtain a 2D location of the obstacle, and transforming the 2D location of the obstacle into a 3D location of the obstacle based on the depth channel data.

Abstract: A human-object scene recognition method includes: acquiring an input RGB image and a depth image corresponding to the RGB image; detecting objects and humans in the RGB image using a segmentation classification algorithm based on a sample database; in response to detection of objects and/or humans, performing a segment detection to each of the detected objects and/or humans based on the ROB image and the depth image, and acquiring a result of the segment detection; calculating 3D hounding boxes for each of the detected objects and/or humans according to the result of the segment detection, and determining a position of each of the detected objects and/or humans according to the 3D bounding boxes.

Abstract: Response methods to human abnormal behaviors for a mobility aid robot having a user-facing camera are disclosed. The mobility aid robot responds to human abnormal behaviors by detecting a face of a human during the robot aiding the human to move through the camera, comparing an initial size of the face and an immediate size of the face in response to the face of the human having detected during the robot aiding the human to move, determining the human as in abnormal behavior(s) in response to the immediate size of the face being smaller than the initial size of the face, and performing response(s) corresponding to the abnormal behavior(s) in response to the human being in the abnormal behavior(s), where the response(s) include slowing down the robot.

Abstract: Human lying posture detections are disclosed. A human lying on a bed is detected by obtaining an image through a depth camera, detecting objects in the image and marking the objects in the image using 2D bounding boxes by deep learning, determining the human being in a lying posture in response to a width and a height of the 2D bounding box of the human meeting a predetermined condition, detecting one or more skin areas in the image and generating skin area 2D bounding boxes to mark each of the one or more skin areas using a skin detection algorithm, and determining the human being in the lying posture in response to the skin area 2D bounding boxes and the 2D bounding box of the bed meeting a predetermined positional relationship.

Abstract: Human posture determination is disclosed. Human posture is determined by obtaining range image(s) through a range camera, detecting key points of an estimated skeleton of a human in color data of the range image(s) and calculating positions of the detected key points based on depth data of the range image(s), choosing a feature map from a set of predefined feature maps based on the detected key points among a set of predefined key points, obtaining two features of a body of the human corresponding to the chosen feature map based on the positions of the detected key points, and determining a posture of the human according to the two features in the chosen feature map.

Abstract: Carpet detection using an RGB-D camera and mobile machine movement control based thereon are disclosed. Carpets and carpet curls are detected by obtaining a RGB-D image pair including an RGB image and a depth image through an RGB-D camera, detecting carpet and carpet-curl areas in the RGB image and generating a 2D bounding box to mark each area using a deep learning model, and generating groups of carpet and carpet-curt points corresponding to each of the carpet and carpet-curl areas by matching each pixel of the RGB image within each 2D bounding box corresponding to the carpet and carpet curl areas to each pixel in the depth image.

Abstract: Navigation of a mobility aid robot having a camera and gripping part(s) disposed toward different directions is disclosed. The mobility aid robot is navigated to approach a user by identifying a posture of the user through the camera, determining a mode of the robot according to a type of the specified task to be performed on the user and the identified posture of the user, controlling the robot to move according to a planned trajectory corresponding to the determined mode of the robot, and turning the robot upon reaching the desired pose such that the gripping part faces the user, in response to the determined mode of the robot corresponding to the specified task of an assisting type and the user at one of a standing posture and a sitting posture.

Abstract: On-floor obstacle detection using an RGB-D camera is disclosed. An obstacle on a floor is detected by receiving an image including depth channel data and RGB channel data through the RGB-D camera, estimating a ground plane corresponding to the floor based on the depth channel data, obtaining a foreground of the image corresponding to the ground plane based on the depth channel data, performing a distribution modeling on the foreground of the image based on the RGB channel data to obtain a 2D location of the obstacle, and transforming the 2D location of the obstacle into a 3D location of the obstacle based on the depth channel data.