Abstract: A semiconductor package apparatus may include technology to provide an image to a low power shallow hash network, generate a hash code from the low power shallow hash network, and identify one or more similar images based on the hash code. Other embodiments are disclosed and claimed.

Abstract: In one embodiment, an apparatus comprises a storage device and a processor. The storage device may store a plurality of compressed images comprising one or more compressed master images and one or more compressed slave images.

Abstract: A mechanism is described for facilitating protection and recovery of identities in surveillance camera environments according to one embodiment. An apparatus of embodiments, as described herein, includes detection and reception logic to receive a video stream of a scene as captured by a camera, wherein the scene includes persons. The apparatus may further include recognition and application logic to recognize an abnormal activity and one or more persons associated with the abnormal activity in a video frame of the video stream. The apparatus may further include identity recovery logic to recover one or more identities of the one or more persons in response to the abnormal activity, where the one or more identities are recovered from masked data and encrypted residuals associated with the one or more persons.

Abstract: In one embodiment, an apparatus comprises a processor to: identify a workload comprising a plurality of tasks; generate a workload graph based on the workload, wherein the workload graph comprises information associated with the plurality of tasks; identify a device connectivity graph, wherein the device connectivity graph comprises device connectivity information associated with a plurality of processing devices; identify a privacy policy associated with the workload; identify privacy level information associated with the plurality of processing devices; identify a privacy constraint based on the privacy policy and the privacy level information; and determine a workload schedule, wherein the workload schedule comprises a mapping of the workload onto the plurality of processing devices, and wherein the workload schedule is determined based on the privacy constraint, the workload graph, and the device connectivity graph.

Abstract: Technologies for detecting interactions with surfaces from a spherical view of a room include a compute device. The compute device includes an image capture manager to obtain one or more images that depict a spherical view of a room that includes multiple surfaces. Additionally, the compute device includes a surface interaction detection manager to detect, from the one or more images, a person in the room, generate a bounding box around the person, preprocess the bounding box to represent the person in an upright orientation, determine a pose of the person from the preprocessed bounding box, detect an outstretched hand from the determined pose, and determine, from the detected outstretched hand, a surface of interaction in the room.

Abstract: A mechanism is described for facilitating age classification of humans using image depth and human pose according to one embodiment. A method of embodiments, as described herein, includes facilitating, by one or more cameras of a computing device, capturing of a video stream of a scene having persons, and computing overall-depth torso lengths of the persons based on depth torso lengths of the persons. The method may further include comparing the overall-depth torso lengths with a predetermined threshold value representing a separation age between adults and children, and classifying a first set of the persons as adults if a first set of the overall-depth torso lengths associated with the first set of persons is greater than the threshold value.

Abstract: Methods, apparatus, systems and articles of manufacture to improve efficiency of object tracking in video frames are disclosed. An example apparatus includes a clusterer to cluster a map of a video frame into blobs; a comparator to determine an intersection over union value between the blobs and bounding boxes in a second video frame; and an interface to initiate object detection by a neural network on the first video frame when the intersection over union does not satisfy a threshold.

Abstract: An example apparatus for encoding video frames includes a receiver to receive events from a dynamic vision sensor and a video frame from an image sensor. The apparatus also includes a heat map generator to generate a heat map based on the received events. The apparatus further includes a region of interest (ROI) map generator generate a ROI map based on the heat map. The apparatus includes a parameter adjuster to adjust an encoding parameter based on the ROI map. The apparatus also further includes a video encoder to encode the video frame using the adjusted parameter.

Abstract: A mechanism is described for facilitating age classification of humans using image depth and human pose according to one embodiment. A method of embodiments, as described herein, includes facilitating, by one or more cameras of a computing device, capturing of a video stream of a scene having persons, and computing overall-depth torso lengths of the persons based on depth torso lengths of the persons. The method may further include comparing the overall-depth torso lengths with a predetermined threshold value representing a separation age between adults and children, and classifying a first set of the persons as adults if a first set of the overall-depth torso lengths associated with the first set of persons is greater than the threshold value.

Abstract: In one embodiment, an apparatus comprises processing circuitry to: receive, via a communication interface, a compressed video stream captured by a camera, wherein the compressed video stream comprises: a first compressed frame; and a second compressed frame, wherein the second compressed frame is compressed based at least in part on the first compressed frame, and wherein the second compressed frame comprises a plurality of motion vectors; decompress the first compressed frame into a first decompressed frame; perform pixel-domain object detection to detect an object at a first position in the first decompressed frame; and perform compressed-domain object detection to detect the object at a second position in the second compressed frame, wherein the object is detected at the second position in the second compressed frame based on: the first position of the object in the first decompressed frame; and the plurality of motion vectors from the second compressed frame.

Abstract: Methods and apparatus for controlled shadow casting to increase the perceptual quality of projected content are disclosed. In some examples, an apparatus is to increase a perceptual quality of content projected onto a projection surface. In some examples, the apparatus includes a processor and memory. In some examples, the memory includes computer readable instructions. In some examples, the instructions, when executed, cause the processor to determine a target shutter position for a shutter based on a location of a light source and a location of a projection surface. In some examples, the instructions, when executed, further cause the processor to move the shutter to the target shutter position to cast a shadow onto the projection surface around a portion of content projected onto the projection surface.

Abstract: Techniques related to applying computer vision to decompressed video are discussed. Such techniques may include generating a region of interest in an individual video frame by translating spatial indicators of a first detected computer vision result from a reference video frame to the individual video frame and applying a greater threshold within the region of interest than outside of the region of interest for computer vision evaluation in the individual frame.

Abstract: An example apparatus for estimating poses includes a person estimator to estimate a number of people based on a significant head count of received refined part detections. The apparatus includes a detection clusterer to cluster the refined part detections based on the estimated number of people to generate clustered part detections. The apparatus includes a candidate selector to select candidate person clusters for each clustered part detection based on proximity to the clustered part detection. The apparatus includes a sequential assigner to calculate a cluster affinity score for each combination of candidate person cluster and clustered part detection, and greedily sequentially assign each clustered part detection to a candidate person cluster based on the cluster affinity score to generate person clusters. The apparatus includes a pose generator to generate a pose for each person cluster.

Abstract: Techniques related to applying computer vision to decompressed video are discussed. Such techniques may include generating a region of interest in an individual video frame by translating spatial indicators of a first detected computer vision result from a reference video frame to the individual video frame and applying a greater threshold within the region of interest than outside of the region of interest for computer vision evaluation in the individual frame.

Abstract: An example apparatus for encoding video frames includes a receiver to receive video frames and a heat map from a camera and expected object regions from a video database. The apparatus also includes a region of interest (ROI) map generator to detect a region of interest in a video frame based on the expected object regions. The ROI map generator can also detect a region of interest in the video frame based on the heat map. The ROI map generator can then generate an ROI map based on the detected regions of interest. The apparatus further includes a parameter adjuster to adjust an encoding parameter based on the ROI map. The apparatus also further includes a video encoder to encode the video frame using the adjusted encoding parameter.

Abstract: A semiconductor package apparatus may include technology to provide an image to a low power shallow hash network, generate a hash code from the low power shallow hash network, and identify one or more similar images based on the hash code. Other embodiments are disclosed and claimed.

Abstract: In one embodiment, an apparatus comprises a storage device and a processor. The storage device may store a plurality of compressed images comprising one or more compressed master images and one or more compressed slave images.

Abstract: In one embodiment, an apparatus comprises a communication interface and a processor. The communication interface is to communicate with a plurality of devices. The processor is to: receive compressed data from a first device, wherein the compressed data is associated with visual data captured by sensor(s); perform a current stage of processing on the compressed data using a current CNN, wherein the current stage of processing corresponds to one of a plurality of processing stages associated with the visual data, and wherein the current CNN corresponds to one of a plurality of CNNs associated with the plurality of processing stages; obtain an output associated with the current stage of processing; determine, based on the output, whether processing associated with the visual data is complete; if the processing is complete, output a result associated with the visual data; if the processing is incomplete, transmit the compressed data to a second device.

Abstract: 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.

Abstract: Techniques related to applying computer vision to decompressed video are discussed. Such techniques may include generating a region of interest in an individual video frame by translating spatial indicators of a first detected computer vision result from a reference video frame to the individual video frame and applying a greater threshold within the region of interest than outside of the region of interest for computer vision evaluation in the individual frame.