Machine learning systems and methods are disclosed for prediction of wound healing, such as for diabetic foot ulcers or other wounds, and for assessment implementations such as segmentation of images into wound regions and non-wound regions. Systems for assessing or predicting wound healing can include a light detection element configured to collect light of at least a first wavelength reflected from a tissue region including a wound, and one or more processors configured to generate an image based on a signal from the light detection element having pixels depicting the tissue region, determine reflectance intensity values for at least a subset of the pixels, determine one or more quantitative features of the subset of the plurality of pixels based on the reflectance intensity values, and generate a predicted or assessed healing parameter associated with the wound over a predetermined time interval.

A safety belt detection method, apparatus, computer device and computer readable storage medium are disclosed. The safety belt detection method includes the steps as follows. An image to be detected is obtained. The image to be detected is inputted into a detection network which includes a global dichotomous branch network and a grid classification branch network. A dichotomous result, which indicates whether a driver is wearing a safety belt and is output from the global dichotomous branch network, is obtained. A grid classification diagram, which indicates a position information of the safety belt and is output from the grid classification branch network, is obtained based on image classification. A detection result of the safety belt, indicating whether the driver is wearing the safety belt normatively, is obtained based on the dichotomous result and the grid classification diagram.

A light emitting unit emits infrared rays. An imaging element converts incident infrared rays into an electric signal and outputs the electric signal. A control unit estimates a light emission timing at which infrared rays are emitted from another infrared imaging device based on an infrared picture generated based on the electrical signal output from the imaging element, and performs control to cause the light emitting unit to emit infrared rays in a period in which the infrared rays are not emitted from the another infrared imaging device.

The disclosure describes systems of navigating a hazardous environment. The system includes personal protective equipment (PPE) and computing device(s) configured to process sensor data from the PPE, generate pose data of an agent based on the processed sensor data, and track the pose data as the agent moves through the hazardous environment. The PPE may include an inertial measurement device to generate inertial data and a radar device to generate radar data for detecting a presence or arrangement of objects in a visually obscured environment. The PPE may include a thermal image capture device to generate thermal image data for detecting and classifying thermal features of the hazardous environment. The PPE may include one or more sensors to detect a fiducial marker in a visually obscured environment for identifying features in the visually obscured environment. In these ways, the systems may more safely navigate the agent through the hazardous environment.

Image-based key points detection using a convolutional neural network (CNN) may be impacted if the key points are occluded in the image. Images obtained from additional imaging modalities such as depth and/or thermal images may be used in conjunction with RGB images to reduce or minimize the impact of the occlusion. The additional images may be used to determine adjustment values that are then applied to the weights of the CNN so that the convolution operations may be performed in a modality aware manner to increase the robustness, accuracy, and efficiency of key point detection.

In some embodiments, the system is directed to medical assessment software for analyzing one or more medical conditions and enabling communication between a medical professional and a patient. In some embodiments, the system includes one or more graphical user interfaces configured to enable a medical professional to execute one or more of scheduling a virtual appointment, view a virtual schedule, check patients in/out, enter new patients into the system, request patient recorded outcomes, and view patient progress. In some embodiments, the system is configured to implement an artificial intelligence (AI) algorithm configured to identify one or more unique features within the one or more images and use the one or more unique features as one or more fiducials during an analysis of the one or more images. In some embodiments, the analysis includes a determination of whether an abnormal condition associated with an area of skin is progressing toward healing.

A system for sorting seeds based on their resistance to a stress is disclosed. Batches of purified seeds sorted using the system are also disclosed.

A structured-light projector, a camera assembly, and an electronic device are provided. The structured-light projector includes: a first light source, configured to emit a first light beam; a diffractive optical element, provided on a light-emitting side of the first light source and configured to generate structured light based on the first light beam incident on the diffractive optical element; an optical steering element, provided between the first light source and the diffractive optical element; and a second light source, wherein the second light source includes a light emitter, configured to emit a second light beam, the second light beam comprising infrared light. Via the structured-light projector, a scattered image and an infrared image of the target object can be acquired simutaneously.

An image processing device acquires an image obtained by irradiating an area of a living body with light having a wavelength of 955 [nm] to 2025 [nm]. The image processing device inputs the acquired image to a learned model or a statistical model generated in advance for detecting, from the image, a tumor present in the area, and determines whether or not a tumor is present at each point in the image.

Described herein are systems and methods for determining dryness of produce using image data. A method can include receiving, by a computing system and from an imaging device, image data of a batch of produce, performing, by the computing system, object detection to identify each produce in a frame of the image data, extracting, by the computing system, temperature values in pixels of the identified produce in the frame, and determining, by the computing system, distribution characteristics of the extracted temperature values. The method can also include predicting, by the computing system, a dryness metric for the batch of produce based on applying a trained model to the determined distribution characteristics. The model can be trained using temperature distributions of other produce, the temperature distributions being annotated based on previous mappings of skewness of the temperature distributions to dryness.