A system and method for monitoring a switchgear includes an infrared camera, a processing unit, and an output unit. The infrared camera acquires an infrared image of the switchgear, and the processing unit converts it into a binary image. Pixels in the infrared image having a temperature equal to or above a first threshold value are given the same first value. Pixels in the infrared image having a temperature below the first threshold value are given the same second value. The processing unit is configured to implement a Siamese neural network to determine if a hot spot exists in the infrared image.

An automatic fog identification method using a front camera image and a emergency fog red LED high beam system using the same are proposed. The emergency fog red LED high beam system is configured such that a red LED module is applied to a high beam light source, thus providing a clear and wide view for a driver without diffused reflection even in a foggy situation.

There is provided a vehicle system including a sensing unit, a processing unit, a control unit and a display unit. The sensing unit is configured to capture an image frame containing an eyeball image from a predetermined distance. The processing unit is configured to calculate a pupil position of the eyeball image in the image frame and generate a drive signal corresponding to the pupil position. The control unit is configured to trigger a vehicle device associated with the pupil position according to the drive signal. The display unit is configured to show information of the vehicle device.

There is provided a vehicle system including a sensing unit, a processing unit, a control unit and a display unit. The sensing unit is configured to capture an image frame containing an eyeball image from a predetermined distance. The processing unit is configured to calculate a pupil position of the eyeball image in the image frame and generate a drive signal corresponding to the pupil position. The control unit is configured to trigger a vehicle device associated with the pupil position according to the drive signal. The display unit is configured to show information of the vehicle device.

In measurement using infrared images that are obtained by nighttime aerial photography, a correspondence relationship between the infrared images is determined with high accuracy by the following method. In this method, agricultural land is photographed from the air at night by using an infrared camera mounted on a UAV. In the state in which multiple infrared light emitting points are installed on agricultural land, the agricultural land is photographed multiple times by the infrared camera while the UAV flies at night in such a manner that a part of the agricultural land is commonly contained in multiple infrared photographic images. Then, a correspondence relationship between the multiple infrared photographic images is determined by using bright points of the infrared light emitting points in the part of the agricultural land commonly contained in the infrared photographic images.

A system evaluates currency in an area using image processing. In some examples, the system receives an image of an area from an image sensor, processes the image to identify at least one item of currency in the area, determine a value of the currency irrespective of validity, and counts the currency. In various examples, the system receives an image of an area from an image sensor; processes the image to identify at least one item of currency in the area; determines whether the currency has an error condition; and when the currency is determined to have the error condition, provides output on the error condition. In a number of examples, the system receives an image of an area from an image sensor; processes the image to identify at least one item of currency in the area; determines whether the currency is valid; and when the currency is determined to be suspect, provides output on the currency.

One or more thermal images containing pixel-by-pixel radiation intensity data in two or more wavelength bands can be processed to accurately determine the location of fire within the image(s), regardless of the radiation-scattering effects of smoke. First, all pixels having radiation intensities above a fire threshold in the longer-wavelength band are classified as being aflame. Second, a threshold curve defining a fire threshold in the shorter-wavelength band is applied to the pixels, and those having radiation intensities above the fire threshold in the shorter-wavelength band are classified as being aflame. Third, at least the second group of pixels above is tested to see if each pixel classified as being aflame is part of a group of adjoining pixels which were all classified as being aflame, and if so, each such pixel is reclassified as not being aflame unless it also falls within the first group of pixels above.

A system for quantifying viewer engagement with a video playing on a display includes at least one camera to acquire image data of a viewing area in front of the display. A microphone acquires audio data emitted by a speaker coupled to the display. The system also includes a memory to store processor-executable instructions and a processor. Upon execution of the processor-executable instructions, the processor receives the image data and the audio data and determines an identity of the video displayed on the display based on the audio data. The processor also estimates a first number of people present in the viewing area and a second number of people engaged with the video. The processor further quantifies the viewer engagement of the video based on the first number of people and the second number of people.

The present invention relates to a method for biometric authentication of a user of an electronic device comprising an optical fingerprint sensor arranged under an at least partially transparent display panel and configured to capture an image of an object located on an opposite side of the transparent display panel, the method comprises the steps of: illuminating the object with light of at least one distinguishable color; capturing at least two images of the object with an image sensor comprising a photodetector pixel array while illuminating the object with the light of at least one distinguishable color, wherein the images are captured for different applied forces by the object on the transparent display panel; and performing biometric authentication at least partly based on at least one relationship between the at least two images, the at least one relationship being related to a difference in pixel intensity from pixels in the photodetector pixel array arranged to detect light of the distinguishable color.

The present invention relates to a method for biometric authentication of a user of an electronic device comprising an optical fingerprint sensor arranged under an at least partially transparent display panel and configured to capture an image of an object located on an opposite side of the transparent display panel, the method comprises the steps of: illuminating the object with light of at least one distinguishable color; capturing at least two images of the object with an image sensor comprising a photodetector pixel array while illuminating the object with the light of at least one distinguishable color, wherein the images are captured for different applied forces by the object on the transparent display panel; and performing biometric authentication at least partly based on at least one relationship between the at least two images, the at least one relationship being related to a difference in pixel intensity from pixels in the photodetector pixel array arranged to detect light of the distinguishable color.