Systems and methods for self-supervised representation learning as a means to generate context-specific pretrained models include selecting data from a set of available data sets; selecting a pretext task from domain specific pretext tasks; selecting a target problem specific network architecture based on a user selection from available choices or any customized model as per user preference; and generating a pretrained model for the selected network architecture using the selected data obtained from the set of available data sets and a pretext task as obtained from domain specific pretext tasks.

Systems and methods for semantic labeling of point clouds using images. Some implementations may include obtaining a point cloud that is based on lidar data reflecting one or more objects in a space; obtaining an image that includes a view of at least one of the one or more objects in the space; determining a projection of points from the point cloud onto the image; generating, using the projection, an augmented image that includes one or more channels of data from the point cloud and one or more channels of data from the image; inputting the augmented image to a two dimensional convolutional neural network to obtain a semantic labeled image wherein elements of the semantic labeled image include respective predictions; and mapping, by reversing the projection, predictions of the semantic labeled image to respective points of the point cloud to obtain a semantic labeled point cloud.

A small-object perception system, for use in a vehicle, includes a stereo vision system that captures stereo images and outputs information identifying an object having a dimension in a range of ˜20 cm to about ˜100 cm in a perception range of ˜3 meters to ˜150 meters from the vehicle, and a system controller configured to receive output signals from the stereo vision system and to provide control signals to control a path of movement of the vehicle. The stereo vision system includes cameras separated by a baseline of ˜1 meter to ˜4 meters. The stereo vision system includes a stereo matching module configured to perform stereo matching on left and right initial images and to output a final disparity map based on a plurality of preliminary disparity maps generated from the left and right initial images, with the preliminary disparity maps having different resolutions from each other.

Methods, devices, and systems may be utilized for detecting one or more properties of a plant area and generating a map of the plant area indicating at least one property of the plant area. The system comprises an inspection system associated with a transport device, the inspection system including one or more sensors configured to generate data for a plant area including to: capture at least 3D image data and 2D image data; and generate geolocational data. The datacenter is configured to: receive the 3D image data, 2D image data, and geolocational data from the inspection system; correlate the 3D image data, 2D image data, and geolocational data; and analyze the data for the plant area. A dashboard is configured to display a map with icons corresponding to the proper geolocation and image data with the analysis.

Methods, devices, and systems may be utilized for detecting one or more properties of a plant area and generating a map of the plant area indicating at least one property of the plant area. The system comprises an inspection system associated with a transport device, the inspection system including one or more sensors configured to generate data for a plant area including to: capture at least 3D image data and 2D image data; and generate geolocational data. The datacenter is configured to: receive the 3D image data, 2D image data, and geolocational data from the inspection system; correlate the 3D image data, 2D image data, and geolocational data; and analyze the data for the plant area. A dashboard is configured to display a map with icons corresponding to the proper geolocation and image data with the analysis.

A workpiece image search apparatus includes: a workpiece image deformation unit that generates a third workpiece image by deforming a second workpiece image so that a difference in workpiece shape between a first workpiece image and the second workpiece image becomes smaller, wherein the first workpiece image is obtained by projecting a first workpiece shape of a first workpiece on a two-dimensional plane, and the second workpiece image is obtained by projecting a second workpiece shape of a second workpiece on a two-dimensional plane; and a similarity calculation unit that calculates a similarity between the first workpiece shape and the second workpiece shape by comparing the third workpiece image with the first workpiece image.

A workpiece image search apparatus includes: a workpiece image deformation unit that generates a third workpiece image by deforming a second workpiece image so that a difference in workpiece shape between a first workpiece image and the second workpiece image becomes smaller, wherein the first workpiece image is obtained by projecting a first workpiece shape of a first workpiece on a two-dimensional plane, and the second workpiece image is obtained by projecting a second workpiece shape of a second workpiece on a two-dimensional plane; and a similarity calculation unit that calculates a similarity between the first workpiece shape and the second workpiece shape by comparing the third workpiece image with the first workpiece image.

Systems, methods, and computer-readable for multi-spatial scale object detection include generating one or more object trackers for tracking at least one object detected from on one or more images. One or more blobs are generated for the at least one object based on tracking motion associated with the at least one object. One or more tracklets are generated for the at least one object based on associating the one or more object trackers and the one or more blobs, the one or more tracklets including one or more scales of object tracking data for the at least one object. One or more uncertainty metrics are generated using the one or more object trackers and an embedding of the one or more tracklets. A training module for detecting and tracking the at least one object using the embedding and the one or more uncertainty metrics is generated using deep learning techniques.

The invention provides an image scanning device and an image scanning method. The image scanning device includes: a display that emits red light, green light, and blue light to expose an object when the object contacts the display; the sensor is arranged below the display, and the sensor obtains a first image corresponding to the red light, a second image corresponding to the green light and a third image corresponding to the blue light; and the processing module is coupled to the sensor and the display, and the processing module generates an object image corresponding to the object according to the first image, the second image and the third image.

The invention provides an image scanning device and an image scanning method. The image scanning device includes: a display that emits red light, green light, and blue light to expose an object when the object contacts the display; the sensor is arranged below the display, and the sensor obtains a first image corresponding to the red light, a second image corresponding to the green light and a third image corresponding to the blue light; and the processing module is coupled to the sensor and the display, and the processing module generates an object image corresponding to the object according to the first image, the second image and the third image.