Methods and apparatus for applying data analytics such as deep learning algorithms to sensor data. In one embodiment, an electronic device such as a camera apparatus including a deep learning accelerator (DLA) communicative with an image sensor is disclosed, the camera apparatus configured to evaluate unprocessed sensor data from the image sensor using the DLA. In one variant, the camera apparatus provides sensor data directly to the DLA, bypassing image signal processing in order to improve the effectiveness the DLA, obtain DLA results more quickly than using conventional methods, and further allow the camera apparatus to conserve power.

A method for automatically identifying global solar photovoltaic (PV) panels based on a cloud platform by using remote sensing. Optical images in a study area for a whole specific year are collected based on the cloud platform, and preprocessing is performed to obtain a surface reflectance image. Seven time-series images are derived and constructed based on spectral features of a solar PV panel: a solar PV panel index image, a water index image, a vegetation index image, a difference image between a first shortwave infrared band and a second shortwave infrared band, a difference image between the first shortwave infrared band and a near-infrared band, a blue band image, and a first shortwave infrared band image. Data in the seven time-series images are synthesized and reconstructed to obtain input data required by a model. A remote sensing theoretical model for automatically identifying a solar PV panel is constructed.

A method for automatically identifying global solar photovoltaic (PV) panels based on a cloud platform by using remote sensing. Optical images in a study area for a whole specific year are collected based on the cloud platform, and preprocessing is performed to obtain a surface reflectance image. Seven time-series images are derived and constructed based on spectral features of a solar PV panel: a solar PV panel index image, a water index image, a vegetation index image, a difference image between a first shortwave infrared band and a second shortwave infrared band, a difference image between the first shortwave infrared band and a near-infrared band, a blue band image, and a first shortwave infrared band image. Data in the seven time-series images are synthesized and reconstructed to obtain input data required by a model. A remote sensing theoretical model for automatically identifying a solar PV panel is constructed.

Methods and systems are described herein for generating composite data streams. A data stream processing system may receive multiple data streams from, for example, multiple unmanned vehicles and determine, based on the type of data within each data stream, a machine learning model for each data stream for processing the type of data. Each machine learning model may receive the frames of a corresponding data stream and output indications and locations of objects within those data streams. The data stream processing system may then generate a composite data stream with indications of the detected objects.

The present invention relates to a method for detecting changes in the ore grade of a rock face in near real time. The method includes the step of providing a scanning system having at least a hyperspectral imager, a position system, a LiDAR or range determination unit and computational resources. Further, the method involves determining a precise location of the scanning system utilising the position system. The rock face is scanned with the range determination unit to determine rock face position information. The method involves scanning the rock face with the hyperspectral imager to produce a corresponding rock face hyperspectral image. Further the method involves utilising the computational resources to fuse together the rock face position information and the corresponding rock face hyperspectral image to produce a rock face position and content information map of the rock face.

Provided is an object recognition method which includes obtaining a first visible-light image acquired by the first camera device and a second visible-light image acquired by the second camera device; performing exposure processing on the first visible-light image according to the luminance information of the bright area image of the first visible-light image and performing exposure processing on the second visible-light image according to the luminance information of the dark area images of the first visible-light image and/or the second visible-light image, where the dark area image is an area image having a luminance value less than or equal to the preset value; and performing target object detection on the first visible-light image obtained after exposure processing and the second visible-light image obtained after exposure processing and recognizing and verifying a target object according to the detection result.

An image processing device includes: a light emitting unit that emits a near-infrared ray to a target; a light emission controlling unit that controls a light emission amount of the light emitting unit on a basis of a distance value between the target and the light emitting unit; and a detecting unit that detects a feature point on the basis of a captured image of the target irradiated with the near-infrared ray.

An image processing device includes: a light emitting unit that emits a near-infrared ray to a target; a light emission controlling unit that controls a light emission amount of the light emitting unit on a basis of a distance value between the target and the light emitting unit; and a detecting unit that detects a feature point on the basis of a captured image of the target irradiated with the near-infrared ray.

This application provides an image sensor (702) and image light sensing method. The image sensor (702) includes a red pixel (R), a green pixel (G), a blue pixel (B), and an invisible light pixel, where the red pixel (R), the green pixel (G), and the blue pixel (B) are large pixels, the invisible light pixel is a small pixel, and a light sensing area of the large pixel is greater than that of the small pixel. The red pixel (R), the green pixel (G), and the blue pixel (B) are arranged in a Bayer format. In this application, when color information is sufficient, light crosstalk caused by the small pixel to the large pixel can be reduced, and therefore a signal-to-noise ratio of the large pixel can be improved.

This application provides an image sensor (702) and image light sensing method. The image sensor (702) includes a red pixel (R), a green pixel (G), a blue pixel (B), and an invisible light pixel, where the red pixel (R), the green pixel (G), and the blue pixel (B) are large pixels, the invisible light pixel is a small pixel, and a light sensing area of the large pixel is greater than that of the small pixel. The red pixel (R), the green pixel (G), and the blue pixel (B) are arranged in a Bayer format. In this application, when color information is sufficient, light crosstalk caused by the small pixel to the large pixel can be reduced, and therefore a signal-to-noise ratio of the large pixel can be improved.