Abstract: A defect detection method based on an image of products and an electronic device can accurately determine the error threshold by determining the reconstruction error generated during image reconstruction and by determining the estimated probability generated by the Gaussian mixture model. The test error can then be compared with the error, since the test error and the error threshold are compared numerically, the existence of subtle defects are revealed in the product image, thereby improving the accuracy of defect detection.

Abstract: A method for detecting lane lines, applied in an electronic device, includes: obtaining road images, and obtaining a splice area by performing an image processing on the road images; inputting the splice area into a preset trained lane line detection model and obtaining lane line detection images; and obtaining transformed images and lane line detection results of the transformed images by performing an image transformation on the lane line detection images. The application is able to improve an accuracy of detecting lane lines.

Abstract: A method for segmenting roads in images implemented in an electronic device includes obtaining a road image; obtaining a plurality of regions of interest based on the road image; generating a splicing region based on the plurality of regions of interest; and inputting the splicing region into a pre-trained road segmentation model, and obtaining a road segmentation image and a segmentation result in the road segmentation image.

Abstract: An image defect detection method used in an electronic device, calculates a Kullback-Leible divergence between a first probability distribution and a second probability distribution, and thereby obtains a total loss. Images of samples for testing are input into an autoencoder to calculate a second latent features of the testing sample images and the second reconstructed images. Second reconstruction errors are calculated by a preset error function, as is a third probability distribution of the second latent features, and a total error is calculated according to the third probability distribution and the second reconstruction errors. When the total error is greater than or equal to the threshold, determining that the images of samples for testing reveal defects, and when the total error is less than the threshold, determining that the images of samples for testing reveal no defects.

Abstract: An augmented reality (AR) display is provided. The display comprises a light field generator and a birdbath eyepiece. The light field generator generates a light field as an output. The birdbath eyepiece connects to the light field generator for receiving and projecting the light field to human eye. The birdbath eyepiece comprises a beam splitter and a combiner. The combiner has a curved surface. Each beam of the light field is split into two beams by the beam splitter with one of the split beams reflected by the combiner. Three states-of-use of the birdbath eyepiece are provided for the near-eye light field AR display to transmit the light field to the human eye. A low f-number (or focal ratio) and a large eyebox are obtained to effectively expand the field of view and increase the volume of space within which the human eye can receive the light field.

Abstract: A movement detection method, applied to a navigation input device with a navigation pattern comprising a center pattern and a radial pattern. The movement detection method comprises: (a)capturing a sensing image comprising a center pattern image and at least portion of a radial pattern image by an image sensor, wherein the center pattern image corresponds to the center pattern and the radial pattern image corresponding to the radial pattern; (b)computing a translation of the navigation input device according to shift of the center pattern image; and (c)computing a rotation angle of the navigation input device according to a first pattern relation between the center pattern image and a first portion of the radial pattern image. The translation and the rotation angle can be precisely and sensitively detected even if the joystick device is miniaturized, since the translation and the rotation angle are computed according to the navigation pattern.

Abstract: The invention provides a soluble honokiol derivative (such as a water soluble honokiol derivative) and its application in antagonizing glycoprotein VI receptor and providing antioxidant and neuroprotective effects.

Abstract: A deep recognition model training method applied to an electronic device is provided. The method includes obtaining a ground plane area by segmenting a first image using a ground plane segmentation network. A projection image of the first image is generated based on the first image, an initial depth image corresponding to the first image, and a pose matrix. A target height loss of a depth recognition network is generated, and a depth loss of the depth recognition network is obtained according to a gradient loss between the initial depth image and the first image and a photometric loss between the projection image and the first image. A depth recognition model is obtained by adjusting the depth recognition network based on the depth loss and the target height loss.

Abstract: A method for training a depth recognition model implemented in an electronic device includes determining test objects from test images, and obtaining a first image and a second image; calculating a test projection slope of each test object according to coordinates of each pixel point of each test object in the test images; generating a threshold range according to the plurality of test projection slopes; recognizing a type of terrain corresponding to a position of each initial object; adjusting an initial ground area in the first image, and obtaining a target ground area in the first image; generating a target height loss of a preset depth recognition network, an initial depth image corresponding to the first image, and the target ground area; and adjusting the preset depth recognition network according to the target height loss and a depth loss, and obtaining a depth recognition model for recognizing depth of images.

Abstract: A hand-eye calibration method and a hand-eye calibration device for a robot arm are provided. The method includes following steps. A first mapping relationship between a base of the robot arm and a terminal of the robot arm and a second mapping relationship between a camera and a target object are obtained. Based on a scale, a third mapping relationship between the terminal of the robot arm and a tool set mounted on the terminal and a fourth mapping relationship between the camera and the base in each dimension are updated to minimize an error between a position of the target object in an image captured by the camera and a position of the tool set. In response to the error being convergent and the scale being less than or equal to a scale threshold, the third mapping relationship and the fourth mapping relationship calibrated by the scale are output.

Abstract: A sensing device includes a first substrate, a first sensing element, a first light-shielding layer, a second light-shielding layer and an insulating layer. The first sensing element is disposed on the first substrate. The first light-shielding layer is disposed on the first sensing element and has a first opening, wherein the first opening is completely overlapped with the first sensing element. The second light-shielding layer is disposed on the first light-shielding layer and includes an upper light-shielding part and a lateral light-shielding part, wherein the upper light-shielding part is overlapped with the first light-shielding layer and has a second opening, and the lateral light-shielding part is separated from the upper light-shielding part. The insulating layer is disposed between the first light-shielding layer and the second light-shielding layer, and the lateral light-shielding part covers a sidewall of the insulating layer.

Abstract: An assistance method of safe driving applied in a vehicle-mounted electronic device obtains RGB images of scene in front of a vehicle, processes the RGB images by a trained depth estimation model, obtains depth images and converts the depth images into three-dimensional (3D) point cloud maps, determines 3D regions of interest therein, and obtains position and size information of objects in the 3D regions of interest. When the position information satisfies a first preset condition and/or the size information satisfies a second preset condition, the presence of obstacles in the 3D regions of interest is determined and controls the vehicle to issue an alarm. When the position information does not satisfy the first preset condition and/or the size information does not satisfy the second preset condition, the 3D regions of interest are determined as obstacle-free, and permitting the vehicle to continue driving.

Abstract: A method for detecting defect of images applied in an electronic device inputs flawless sample training images into an autoencoder, and calculates first latent feature by a coding layer of the autoencoder, and calculates first reconstructed images by a decoding layer, and calculates a first reconstruction error by a first preset error function. The electronic device trains the discriminator according to the flawless sample training images and first reconstructed images, and calculates an adversarial learning error, and calculates a sample error, determines an error threshold based on the sample error, and obtains testing sample images, and calculates second latent feature of the testing sample images by the coding layer, and calculates the second reconstructed images of the testing sample images by the decoding layer, and calculate a difference between the testing sample images and the second reconstructed images, thus a detection result of the testing sample images is determined.

Abstract: A method for managing driving applied in an electronic device which assesses distances to objects in a path of autonomous driving obtains RGB images of a scene in front of a vehicle, processes the RGB images based on a trained depth estimation model, and obtain depth images corresponding to the RGB images. The depth images are converted to 3D point cloud maps, 3D regions of interest from the 3D point cloud maps are determined according to a size of the vehicle, and the 3D regions of interest are converted into 2D regions of interest according to internal parameters of a camera. The 2D regions of interest are analyzed for obstacles. Driving continues when the 2D regions of interest have no obstacles, the vehicle is controlled to issue an alarm when obstacles are discovered.

Abstract: A vehicle-borne method for recognizing the illumination state of traffic lights even against a backlighting of strong sunlight or other light source obtains a first image of a set of traffic lights in a road traffic environment. A segmentation map is acquired by dividing a first region from the first image, and an illumination region in the segmentation map is extracted by marking RGB pixels in the region which are of a preset threshold in brightness according to a training model. A lit color of the set of traffic lights is recognized according to a position of the illumination region in the segmentation map. By utilizing the method, accuracy of recognition of illumination state of traffic lights is improved.

Abstract: An optical sensing device includes a substrate, sensing elements, a planarization layer, and a light-shielding layer. The sensing elements are located on the substrate. Each sensing element includes a first net-shaped electrode, a second net-shaped electrode, and a sensing layer. The first net-shaped electrode is located between the sensing layer and the substrate. The sensing layer is located between the first net-shaped electrode and the second net-shaped electrode. The planarization layer is located on the sensing elements and the substrate and has via holes. The light-shielding layer is located on the planarization layer and includes net-shaped light-shielding patterns. The net-shaped light-shielding patterns are overlapped with the second net-shaped electrodes of the sensing elements, respectively, and the net-shaped light-shielding patterns are electrically connected to the second net-shaped electrodes of the sensing elements via the via holes, respectively.

Abstract: A method for detecting road conditions applied in an electronic device obtains images of a scene in front of a vehicle, and inputs the images into a trained semantic segmentation model. The electronic device inputs the images into a backbone network for feature extraction and obtains a plurality of feature maps, inputs the feature maps into the head network, processes the feature maps by a first segmentation network of the head network, and outputs a first recognition result. The electronic device further processes the feature maps by a second segmentation network of the head network, and outputs a second recognition result, and determines whether the vehicle can continue to drive on safely according to the first recognition result and the second recognition result.

Abstract: A pressure detection device of detecting a forced state of a deformable object includes a body, an image sensor and a processor. The body is a deformable hollow structure. The body has an inner surface and an outer surface, and an identifiable vision feature is disposed on the inner surface. The image sensor is disposed inside the body and faces the inner surface of the body, and is adapted to capture a frame containing the identifiable vision feature on the inner surface. The processor is electrically connected with the image sensor, and adapted to analyze position variation of the identifiable vision feature within the captured frame for identifying a motion type of a gesture applied to the outer surface of the body.

Abstract: A sensing device includes a first substrate, a first sensing element, a first light-shielding layer, a second light-shielding layer and an insulating layer. The first sensing element is disposed on the first substrate. The first light-shielding layer is disposed on the first sensing element and has a first opening, wherein the first opening is completely overlapped with the first sensing element. The second light-shielding layer is disposed on the first light-shielding layer and includes an upper light-shielding part and a lateral light-shielding part, wherein the upper light-shielding part is overlapped with the first light-shielding layer and has a second opening, and the lateral light-shielding part is separated from the upper light-shielding part. The insulating layer is disposed between the first light-shielding layer and the second light-shielding layer, and the lateral light-shielding part covers a sidewall of the insulating layer.

Abstract: A light-sensing device comprises a substrate, multiple first working light-sensing elements, multiple second working light-sensing elements, multiple third working light-sensing elements, multiple first reference light-sensing elements, multiple second reference light-sensing elements, multiple third reference light-sensing elements, a first processing element, and a second processing element. The substrate has a first working area, a second working area, a third working area, a first reference area, a second reference area, and a third reference area. The multiple first working light-sensing elements, the multiple second working light-sensing elements, and the multiple third working light-sensing elements are respectively disposed in the first working area, the second working area, and the third working area.