An information processing apparatus creates a dated image data list by classifying a plurality of dated image data, associates the dated image data list with a specific user, acquires the dated image data for a subject, which is similar to a subject of dateless image data, from the dated image data list, and derives a date to be added to the dateless image data, based on the date added to the acquired dated image data. The plurality of dated image data are image data of a plurality of users including the specific user. The dated image data list is created by classifying the plurality of dated image data for each subject. The dated image data list for a subject, which is similar to a subject of the dated image data, is associated with the specific user.

State of art techniques attempt in extracting insights from eye features, specifically pupil with focus on behavioral analysis than on confidence level detection. Embodiments of the present disclosure provide a method and system for confidence level detection from eye features using ML based approach. The method enables generating overall confidence level label based on the subject's performance during an interaction, wherein the interaction that is analyzed is captured as a video sequence focusing on face of the subject. For each frame facial features comprising an Eye-Aspect ratio, a mouth movement, Horizontal displacements, Vertical displacements, Horizontal Squeezes and Vertical Peaks, are computed, wherein HDs, VDs, HSs and VPs are features that are derived from points on eyebrow with reference to nose tip of the detected face. This is repeated for all frames in the window. A Bi-LSTM model is trained using the facial features to derive confidence level of the subject.

A system and method for detecting changes in an agricultural field uses a time series of target images of the agricultural field in which a vegetation index value is calculated for each target image. A target trend line is calculated from the time series of the vegetation index values. A time series of candidate images of one or more candidate fields having one or more attributes that correspond to one or more attributes of the agricultural field is also acquired in which an expected trend line can be determined from calculated vegetation index values representative of respective candidate images. An alert is generated in response to a deviation of the target trend line from the expected trend line that meets alert criteria.

An Artificial Intelligence (AI) ergonomic assessment and positioning system that analyzes remote workspace data, identifies objects that are improperly positioned, oriented, and/or have undesirable settings, and automatically adjusts, moves, sets, and/or provides automatic guidance for the adjustment, movement, and/or setting of target objects in the remote workspace.

Systems and methods are provided for identifying a key instrument in an event. One example method includes receiving a capture of the event and identifying, at a first computing device, the event. The key instrument is identified at the first computing device. An indicator to apply to and/or around the identified key instrument is generated for display.

Techniques are disclosed for determining whether to include a bodyprint in a cluster of bodyprints associated with a recognized person. For example, a device performs facial recognition to identify the identity of a first person. The device also identifies and stores physical characteristic information of the first person, the stored information associated with the identity of the first person based on the recognized face. Subsequently, the device receives a second video feed showing an image of a second person whose face is also determined to be recognized by the device. The device then generates a quality score for physical characteristics in the image of the user. The device can then add the image with the physical characteristics to a cluster of images associated with the person if the quality score is above a threshold, or discard the image if not.

A focus method and an image sensing apparatus are disclosed. The method includes capturing, by a plurality of event sensing pixels, event data of a targeted scene, wherein the event data indicates which pixels of the event sensing pixels have changes in light intensity, accumulating the event data for a predetermined time interval to obtain accumulated event data, determining whether a scene change occurs in the targeted scene according to the accumulated event data, obtaining one or more interest regions in the targeted scene according to the accumulated event data in response to the scene change, and providing at least one of the one or more interest regions for a focus operation. The image sensing apparatus comprises a plurality of image sensing pixels, a plurality of event sensing pixels, and a controller configured to perform said method.

There is provided a vehicle sensor system, comprising: a plurality of sensors with mostly overlapping field of views that simultaneously acquire temporary images, a processing circuitry that: analyzes the temporary images to identify at least one blocked image area in at least one temporary image of the plurality of temporary images which is less or not blocked in at least one spatially corresponding image area of at least one other temporary image of the plurality of temporary images, selects visual data from the at least one spatially corresponding image areas over corresponding visual data from the at least one blocked images area, merges the plurality of temporary images into a final image using the selected visual data and excludes the at least one blocked image area, and an output interface that forwards the final image to a vehicle controller.

There is provided a vehicle sensor system, comprising: a plurality of sensors with mostly overlapping field of views that simultaneously acquire temporary images, a processing circuitry that: analyzes the temporary images to identify at least one blocked image area in at least one temporary image of the plurality of temporary images which is less or not blocked in at least one spatially corresponding image area of at least one other temporary image of the plurality of temporary images, selects visual data from the at least one spatially corresponding image areas over corresponding visual data from the at least one blocked images area, merges the plurality of temporary images into a final image using the selected visual data and excludes the at least one blocked image area, and an output interface that forwards the final image to a vehicle controller.

The present invention proposes an ensemble deep learning method for identifying unsafe behaviors of operators in maritime working environment. Firstly, extract features of maritime images with the You Only Look Once (YOLO) V3 model, and then enhance a multi-scale detection capability by introducing a feature pyramid structure. Secondly, obtain instance-level features and time memory features of the operators and devices in the maritime working environment with the Joint Learning of Detection and Embedding (JDE) paradigm. Thirdly, transfer spatial-temporal interaction information into a feature memory pool, and update the time memory features with the asynchronous memory updating algorithm. Finally, identify the interaction between the operators, the devices, and unsafe behaviors with an asynchronous interaction aggregation network. The proposed invention can accurately determine the unsafe behaviors of the operators, and thus provide operation decisions for maritime management relevant activities.