Systems and methods for training an artificial intelligence (AI) classifier of scanned items. The items may include a training set of sample raw scans. The set may include in-class objects and not-in-class raw scans. An AI classifier may be configured to sample raw scans in the training set, measure errors in the results, update classifier parameters based on the errors, and detect completion of training.

An object capturing device includes light emission, receiving, and scanning units, and distance calculation, and object determination units. The scanning unit measures light from the emission unit to head toward a measurement target space to perform scanning, and to guide reflected light from the object with respect to the measurement light to the receiving unit. The distance calculation unit calculates a distance to the object in association with a scanning angle of the scanning unit. The object determination unit determines whether the object is a capture target based on whether a scanning angle range within which a difference between distances is equal to or less than a predetermined threshold value corresponding to a reference scanning angle range of the capture target, and a determination of whether intensity distribution of the reflected light within the scanning angle range corresponds to reference intensity distribution of the reflected light from the capture target.

An object capturing device includes light emission, receiving, and scanning units, and distance calculation, and object determination units. The scanning unit measures light from the emission unit to head toward a measurement target space to perform scanning, and to guide reflected light from the object with respect to the measurement light to the receiving unit. The distance calculation unit calculates a distance to the object in association with a scanning angle of the scanning unit. The object determination unit determines whether the object is a capture target based on whether a scanning angle range within which a difference between distances is equal to or less than a predetermined threshold value corresponding to a reference scanning angle range of the capture target, and a determination of whether intensity distribution of the reflected light within the scanning angle range corresponds to reference intensity distribution of the reflected light from the capture target.

An object identification and collection method is disclosed. The method includes receiving a pick-up path that identifies a route in which to guide an object-collection system over a target geographical area to pick up objects, determining a current location of the object-collection system relative to the pick-up path, and guiding the object-collection system along the pick-up path over the target geographical area based on the current location. The method further includes capturing images in a direction of movement of the object-collection system along the pick-up path, identifying a target object in the images; tracking movement of the target object through the images, determining that the target object is within range of an object picker assembly on the object-collection system based on the tracked movement of the target object, and instructing the object picker assembly to pick up the target object.

This application relates to a target detection method performed at a computer device. The method includes: obtaining a to-be-detected image; extracting a first image feature and a second image feature corresponding to the to-be-detected image; performing dilated convolution to the second image feature, to obtain a third image feature corresponding to the to-be-detected image; performing classification and regression to the first image feature and the third image feature, to determine candidate position parameters corresponding to a target object in the to-be-detected image and degrees of confidence corresponding to the candidate position parameters; and selecting a valid position parameter from the candidate position parameters according to their corresponding degrees of confidence, and determining a position of the target object in the to-be-detected image according to the valid position parameter. The solutions in this application can improve robustness and consume less time.

Computing systems may support image classification and image detection services, and these services may utilize object detection/image classification machine learning models. The described techniques provide for normalization of confidence scores corresponding to manipulated target images and for non-max suppression within the range of confidence scores for manipulated images. In one example, the techniques provide for generating different scales of a test image, and the system performs normalization of confidence scores corresponding to each scaled image and non-max suppression per scaled image These techniques may be used to provide more accurate image detection (e.g., object detection and/or image classification) and may be used with models that are not trained on modified image sets. The model may be trained on a standard (e.g. non-manipulated) image set but used with manipulated target images and the described techniques to provide accurate object detection.

Computing systems may support image classification and image detection services, and these services may utilize object detection/image classification machine learning models. The described techniques provide for normalization of confidence scores corresponding to manipulated target images and for non-max suppression within the range of confidence scores for manipulated images. In one example, the techniques provide for generating different scales of a test image, and the system performs normalization of confidence scores corresponding to each scaled image and non-max suppression per scaled image These techniques may be used to provide more accurate image detection (e.g., object detection and/or image classification) and may be used with models that are not trained on modified image sets. The model may be trained on a standard (e.g. non-manipulated) image set but used with manipulated target images and the described techniques to provide accurate object detection.

A graphical user interface may provide a digital map that includes digital marks for utility lines and excavation boundary. To determine the location information of a ground mark, a computing server may receive an image of a street view of a site and identify one or more ground marks from the image. The computing server may receive geographic information system (GIS) data, which records surveyed location information of benchmarks at the site. The computing server may identify, using an object recognition algorithm, pixels in the image of the street view that correspond to the benchmarks recorded in the GIS data. The computing server may determine, based on relative distances between the pixels that correspond to the benchmarks and the ground marks, location data of the ground marks. The computing server may transmit the location data for display in a digital map that includes digital marks corresponding to the ground marks.

Techniques for identifying pixel groups representing objects in an image include using images having multiple groups of pixels, grouped such that each pixel group represents a zone of interest and determining a pixel value for pixels within each pixel group based on a comparison of pixel values for each individual pixel within the group. A probability heat map is derived from the pixel group values using a first neural network using the pixel group values as input and produces the heat map having a set of graded values indicative of the probability that the respective pixel group includes an object of interest. A zone of interest is identified based on whether the groups of graded values meet a determined probability threshold objects of interest are identified within the at least one zone of interest by way of a second neural network.

In one embodiment, an apparatus comprises a memory and a processor. The memory is to store visual data associated with a visual representation captured by one or more sensors. The processor is to: obtain the visual data associated with the visual representation captured by the one or more sensors, wherein the visual data comprises uncompressed visual data or compressed visual data; process the visual data using a convolutional neural network (CNN), wherein the CNN comprises a plurality of layers, wherein the plurality of layers comprises a plurality of filters, and wherein the plurality of filters comprises one or more pixel-domain filters to perform processing associated with uncompressed data and one or more compressed-domain filters to perform processing associated with compressed data; and classify the visual data based on an output of the CNN.