59results about How to "Reduced Clarity Requirements" patented technology

The invention discloses a method based on monocular vision for detecting and roughly positioning the edge of a road, and relates to the field of machine vision and intelligent control. Aiming at a continuous road with different edge characteristics, two road edge detection methods are supplied and suitable for semistructured and nonstructured roads and can be applied to vision navigation and intelligent control over a robot. The invention provides a method for detecting the edge of the road based on colors and a method for detecting the edge of the road based on threshold value partitioning. On the basis of the obtained edge of the road, an image is subjected to inverted perspective projection transformation, so that a front view is transformed into a top view; and according to a linear corresponding relation between a pixel and an actual distance in the image, a perpendicular distance from the current position of the robot to the edge of the road and a course angle of the robot can be calculated. The method is easy to implement, high in anti-interference performance, high in instantaneity and suitable for the semistructured and nonstructured roads.

The invention relates to an electronic apparatus 10 comprising a body 14 about which a collapsible flexible display 16 is wrapped. In accordance with the invention the body 14 comprises an area 16a on which the flexible display is conceived to overlay in its extended state. This area may be provided with illumination unit for enabling a front illumination of the display in use and/or with a touch-sensitive area 13 for enabling touch functionality in use.

An IC card includes at least one plastic layer, a battery and at least one electronic device embedded in the plastic layer. The battery is electrically connected to the electronic device for providing power to the device. The battery includes an anode, a cathode, and at least one polymer matrix electrolyte (PME) separator disposed between the anode and the cathode. The PME separator includes a polyimide, at least one lithium salt and at least one solvent all intermixed. The PME is substantially optically clear and stable against high temperature and pressure, such as processing conditions typically used in hot lamination processing or injection molding.

The invention provides a video-based safety cap wearing condition detection method comprising the following steps: obtaining video images, and calculating two-frame gray scale difference values so asto find out a motion area; using an agglomerate detection method to find out a candidate area; carrying out deformable assembly model system detection for the candidate area, and finding a clear target head shoulder area; carrying out cascade system detection for the head shoulder area so as to find out the target head area; carrying out HSV color space conversion for the video image head area; using a nerve network to classify and determine the head area image under the HSV color space, and determining whether the target has worn a safety cap or not; using the HSV color space to determine thesafety cap color; finally outputting the head area and safety cap wearing detection result. The video-based safety cap wearing condition detection method is accurate in detection result, can reduce the detection difficulty, and can improve the detection efficiency.

Computer-implemented apparatus, system, and method of generating digital content with various degrees of obfuscation applied. A publisher of content, such as a private or commercial publisher of digital content, may set access restrictions to the content, such as to obfuscate and/or de-obfuscate the content based on select criteria.

An exemplary touch panel display includes a display panel, a backlight module, two infrared cameras, and a processor. The display panel has a touch surface. The backlight module includes a light guide plate and a light source module. The light source module includes a first visible light source and a second infrared light source. The light guide plate is capable of transmitting the visible light and the infrared light through to the display panel. The infrared cameras are disposed in the light guide plate. The infrared cameras are to detect infrared light that is reflected from an object in contact with or adjacent the touch surface of the display panel and form images based on the detected infrared light. The processor is to receive the images outputted from the infrared cameras, and process the images to obtain a position of the object at the touch surface.

A spit prevention mask comprises a frame, the covering plate and two support arms. The covering plate is capable of being inserted onto the frame, two support arms can be attached onto the two ends of the frame. wherein with the above mentioned structure, the ear hook of each support arm can be placed around the user's ear, and the covering plate covers the user's mouth, and the separator keeps a predetermined distance between the covering plate and the user's mouth without any contact; therefore, the covering plate prevents spit coming from the user without reducing the clarity of speech of the user, allows facial expressions to be seen, does not affect intake of breath, and exhalations from the user do not cause fogging of the user's eyeglasses.

The invention relates to a conveyor belt ore rock particle image segmentation method. The method comprises the following steps: 101, preprocessing a to-be-segmented conveyor belt ore rock particle image, and inputting the to-be-segmented conveyor belt ore rock particle image into a pre-trained first convolutional neural network model to obtain a first contour map; 102, inputting the first contourmap into a pre-trained second convolutional neural network model to obtain a second contour map; 103, performing binarization processing on the second contour map by using a preset threshold, and performing morphological closed operation processing on the binarized map to obtain a third contour map; 104, obtaining the contour, the minimum bounding rectangle of the contour and the area of the contour in the third contour map, screening by using the minimum bounding rectangle of the contour and the area of the contour, and drawing the screened contour as a segmentation map. According to the method, deep learning is utilized to realize conveyor belt ore rock image contour detection and ore rock size distribution automatic statistics, the requirement for image definition is reduced, image segmentation is accurate, and application is convenient.

A method is disclosed for a stereoscopic display system. The display system has a display panel containing an array of display units and a plurality of stereoscopic devices coupled to the display panel to affect three-dimensional (3D) display. The method includes receiving a 3D image to be displayed on the array of display units. The method also includes determining original display values for the display units and determining a coupling relationship between the display units and the stereoscopic devices. Further, the method includes determining a crosstalk condition based on the coupling relationship, and adjusting the original display values of display units based on the coupling relationship, the crosstalk condition, and the original display values of both the left display units and the right display units such that the crosstalk condition is cancelled. The method also includes displaying the 3D image using the adjusted display values of the display units.

A transparent display panel and a transparent display device including the same are disclosed. The transparent display panel includes a display region and a non-display region. The display region includes a plurality of light-emitting regions, a plurality of transmissive regions, a plurality of line regions spaced from each other and arranged in one direction, and a plurality of pixel circuit regions electrically connected to the light-emitting regions respectively to drive the light-emitting regions. Alternately-arranged adjacent line regions include alternately-arranged adjacent VSS voltage connection line and VDD voltage connection line, respectively. Thus, a new pixel arrangement structure that may increase or maximize a transparent area of a bezel and reduce or minimize a haze value without reducing transmittance of the display region may be realized.

The invention discloses a weld joint forming prediction method based on a complementary dual-channel convolutional neural network. Compared with a BP neural network, the convolutional neural network has the biggest characteristic that the extraction of molten pool characteristics is not needed, but the extraction of molten pool characteristic quantity is automatically carried out through a constructed multi-layer convolution kernel; the convolutional neural network takes the whole molten pool image as the input of the model, so that the time consumed for extracting the feature quantity of the molten pool is saved. Meanwhile, the loss of molten pool image information is avoided; compared with a common two-channel convolutional neural network laser welding seam forming prediction method, the method adopts two convolution modules to extract shallow layer features of the molten pool image to extract edge lines of the molten pool, and adopts a two-channel strategy, so that the obtained molten pool image features are more sufficient; laser welding process parameters are introduced by adopting a full-connection module to jointly predict the welding seam morphology of the T-shaped joint, so that the prediction performance of the model can be further improved.

The invention discloses a liquid electronic chemical quantitative filling machine. The machine comprises a purifying cabinet, a transmission mechanism, a filling mechanism, and a tank. The cleaning grade of the purifying cabinet is 100 grades or more, and an inlet and an outlet are respectively arranged in the two sides of the purifying cabinet. The transmission mechanism comprises a conveying belt which is used to deliver a package barrel in/out the purifying cabinet. The conveying belt enters the purifying cabinet from the inlet, goes out of the purifying cabinet from the outlet, and extends out the purifying cabinet from the two ends. The filling mechanism is arranged in the purifying cabinet, and comprises at least one filling gun which is communicated with the tank. The filling gun is provided with a delay switch which is used to control the filling time, and the liquid outlet of the filling gun is downward and points to the conveying belt. The tank is provided with a non-touch type liquid level monitor and control device, which is electrically connected to a first electromagnetic valve. The liquid inlet pipeline of the tank is provided with a first pneumatic diaphragm adjusting valve, and the first electromagnetic valve is arranged on the gas source channel of the first pneumatic diaphragm adjusting valve.

The invention discloses an intelligent ship identity recognition method and system based on a twin network. The method comprises steps: constructing the twin network based on a deep convolutional neural network, manufacturing a ship name picture sample data set, and training the twin network by using the data set. The ship name information of the ship board position can be accurately matched and recognized, and the ship identity information can be intelligently recognized. According to the invention, the ship identity can be intelligently identified based on the ship video image, water supervisors are helped to better identify the real identity of the ship and acquire detailed information of the ship, and compared with other methods using artificial intelligence, such as a ship shape feature extraction method and an optical character-based identification method, the provided method is characterized in that the required requirements on definition of required training picture set are low, quantity requirements are low, the training picture set is easier to obtain, the detection accuracy is higher, the ship identification range can be conveniently expanded, and the method has the capability of being applied to actual engineering.

A packaged product formed by enclosing a content material, such as food or beverage, sanitary products or medical products, within a packaging material including at least a layer of hydrophilic resin, is heat-treated with hot water for, e.g., boil sterilization or retort sterilization. The hot water is caused to contain a water-soluble compound in an amount substantially exceeding a level contained in tap water, whereby it becomes possible to suppress the opalescence of the packaging material causing inferior appearance or transparency and leading to a lowering in gas-barrier property, which has been problematic in the conventional boil or retort hot water treatment.

The invention provides an unmanned aerial vehicle landing method and device, a parking apron and electronic equipment, and the method comprises the steps: obtaining a first target image currently collected by an unmanned aerial vehicle, wherein the first target image comprises a part icon on the surface of the parking apron, and the part icon is formed by a plurality of components of the parking apron; determining the relative position of the unmanned aerial vehicle relative to the parking apron according to the position information of the component icon in the first target image; and according to the relative position of the unmanned aerial vehicle relative to the parking apron, adjusting landing flight parameters of the unmanned aerial vehicle, wherein the landing flight parameters comprise attitude parameters. According to the method, the relative position of the parking apron and the unmanned aerial vehicle can be accurately determined when the unmanned aerial vehicle is at a relatively high height, so that accurate landing of the unmanned aerial vehicle is realized.