113 results about "Visual perception" patented technology

The invention discloses a hybrid image compressing method based on block classification. In the invention, blocks are divided into text/ image block, natural image block and hybrid block according to different features of text/image area and natural image area of original images in the aspect of color and texture; then a compression mode in which palette coding, Hextile coding and LZW coding are combined is used in the text/ image block, a JPEG lossy compression mode is used in the natural image while the algorithm of the combination of the two modes is used in the hybrid block. The invention has the advantages that based on the block classification method, the text/image area and the natural image area can be divided up accurately, and that the blocks are respectively encoded can keep rather acuminate edge of the text/image block so as to enhance visual effect on the basis of ensuring higher compression efficiency and upgrade the peak signal to noise ratio of reconstructed images; the complexity of the algorithm is lower.

A device and methods for performing a closed-chain exercise for the lower extremities of a human subject and, in particular, the legs, using stimulation. The device may include a sled for receiving the subject and for translating to and fro between a first, lower position in which the legs are at least partially bent and a second, higher position in which the legs are less bent than in the first position. A stimulator is provided for facilitating the performance of the closed-chain leg exercise by the subject to move the sled between the first and second positions, either by way of electrical signals provided directly to the applicable muscles or by way of sensory (e.g., visual) stimulation, with or without electro-muscular stimulation. In another aspect, adaptive feed-forward control may also be used to enhance the exercise regimen performed using the device.

A computer-controlled system determines attributes of a frexel, an area of human skin, and applies an electrostatically charged modifying agent (RMA) at the pixel level, to make the skin appear more attractive. The system scans the frexel, identifies unattractive attributes, charges the RMA with an electrostatic charger, and applies the RMA, typically with an inkjet printer. The identified attributes relate to reflectance and may refer to features such as irregular-looking light and dark spots, age-spots, scars, and bruises. Identified attributes may also relate to the surface topology of the skin, for more precisely enhancing surface irregularities. Feature mapping may be used, for example to make cheeks appear pinker and cheekbones more prominent. The charged RMA can be applied in agreement with identified patterns, such as adding red to a red frexel, or in opposition, such as adding green or blue to a red frexel, according to idealized models of attractiveness.

A music application guides a user with some musical experience through the steps of creating and editing a musical enhancement file that enhances and plays in synchronicity with an audio signal of an original artist's recorded performance. This enables others, perhaps with lesser musical ability than the original artist, to play-along with the original artist by following melodic, chordal, rhythmic, and verbal prompts. The music application accounts for differences in the timing of the performance from a standard tempo by guiding the user through the process of creating a tempo map for the performance and by associating the tempo map with MIDI information of the enhancement file. Enhancements may contain MIDI information, audio signal information, and/or video signal information which may be played back in synchronicity with the recorded performance to provide an aural and visual aid to others playing-along who may have less musical experience.

The invention relates to an uncalibration machine vision-based intelligent navigation control system and an uncalibration machine vision-based intelligent navigation control method, and belongs to the technical field of automation and detection. In order to overcome the disadvantage that whether a technical effect is good or bad depends on uncalibration parameters in a conventional scheme, in vision system-based mobile robot real-time obstacle avoidance and a navigation control method in the technical scheme of the invention, an image is automatically acquired and analyzed for the purpose of realizing the control of a mobile robot platform; the image is processed rapidly from image feedback information obtained directly by utilizing the principal of machine vision; and feedback information is given in a time as short as possible for participating in the generation of a control decision so as to form the position closed-loop control of an end effector of the mobile robot. The scheme improves the adaptability and the work efficiency of a robot, effectively maintains the speed and the precision in an image processing process, enhances the robustness and the stability of a robot control system, and reduces cost input and energy consumption in an implementation process of the technical scheme.

The invention provides a full-automatic three-dimension characteristic extracting method. The method comprises the steps of firstly converting the three-dimension point clouds of all single view fields obtained by a stereoscopic vision measuring system into depth images of a single view field; splicing the point clouds of the single view fields; carrying out automatic searching and extracting on the corresponding depth images according to the known positioning characteristic of a workpiece to obtain the positioning characteristic of the workpiece, thus automatically converting the spliced three-dimension point clouds into the workpiece coordinate system; subsequently inputting the ideal coordinates of all characteristics to be detected of the workpiece in the workpiece design model; dividing the characteristics into a plurality of types such as aperture, tendon, plane and the like; automatically extracting the depth images respectively and obtaining the two-dimension coordinates of depth images; searching the three-dimension points of two-dimension depth image coordinates under the corresponding workpiece coordinate system; and obtaining the three-dimension information of each characteristic by calculation. The method has the characteristics of full automation, good flexibility and good expandability, and can be used for automatically extracting three-dimension characteristicsof various workpieces with known positioning characteristics.

A taught position modification device easily correcting, in a short time, positions of taught points in a program prepared by an offline programming system. A workpiece image captured by a visual sensor and an image of a three-dimensional workpiece model having three characteristic points are displayed on a screen. Based on coordinate values of workpiece portions corresponding to the characteristic points which are specified in the workpiece image, the position and orientation of the model in a robot operating space are corrected, and also positions of taught points are corrected. When a tool end of a robot is positioned by jog feed to the operation position on a workpiece after being automatically moved to one of the corrected taught points, the taught point is modified based on the robot operating position detected at that time.

A patient immobilization device for immobilizing a patient and performing a diagnostic evaluation of such patient is comprised of a backboard, a structure configured to support the head of a patient on the backboard, and a pupil-sizing indicator positioned on a surface of the support structure to be visually accessible to a person that is visually evaluating the head and face of an immobilized patient on the backboard.

The invention discloses a track detection method and a robot. The track detection method comprises the following steps of: acquiring a real-time video flow of a track by the robot; determining a position of the robot through vision positioning on the basis of the real-time video flow; determining an advancing scheme of the robot according to the position of the robot; controlling the robot to advance according to the advancing scheme; detecting whether a target image exists in each frame of image of the real-time video flow or not, wherein the target image is an image displaying a fault area of the track; and if the target image exists in each frame of image of the real-time video flow, uploading the target image to a server so that the server carrying out secondary analysis on the targetimage and matching the target image to a corresponding client to display on the basis of a result of the secondary analysis. According to the method, basic facilities and basic equipment of track traffic can be automatically detected, so as to ensure safe operation of track traffic systems.

The invention discloses a machine vision-based spatial position detection system for automobile wheel planes and rims in the field of automobile industry, and aims to solve the problem that spatial positions of the automobile wheel planes and rims cannot be measured. The system comprises a first camera (1), a first line laser (2), a second line laser (3), a third line laser (4), a laser positioning seat (5), a third positioning bolt (6), a second positioning bolt (7), a first positioning bolt (8), longitudinal bubbles (9), a second camera (10), a camera frame (11), a base (12), transverse bubbles (13) and a bottom plate (14). The detection system can finish non-contact and automatic detection of the spatial positions of the automobile wheel planes and rims.

The invention discloses a method for searching a gas leakage source by dynamically integrating a plurality of search strategies. The method comprises a stage of estimating adaptability of various search methods under different search conditions by means of an artificial neural network to determine a main factor which affects performance of various searching methods, and train the artificial neural network for estimating the adaptability of the search methods; an integration mode of a plume finding phase, namely, an integration strategy which combines the search method based on a visual attention mechanism with a random search method; an integration mode of a plume tracing phase, namely, respectively determining a search direction of the next step by a chemotaxis method, an anemotaxis method and a visual method when a robot detects the gas concentration information, and inputting the current search condition which is the main factor affecting the performance of the search methods to the trained artificial neural network to obtain the adaptability of various methods, and planning a local search route of the robot by a driving force vector composition method. The method can obviously improve the efficiency and the success rate of searching the gas leakage source.

The application relates to the technical field of computer vision, and discloses an obstacle avoidance reminding method, a related device and a computer readable storage medium. According to the obstacle avoidance reminding method, the related device and the computer readable storage medium, ground detection is carried out according to acquired image data to acquire ground information of a road; according to the acquired ground information, the traffic condition of the road is determined; if the road is determined to be impassable, road condition detection is carried out on the road to obtaina first detection result, and obstacle detection is carried out on the road to obtain a second detection result; and according to the first detection result and the second detection result, obstacle avoidance reminding information is determined. Ground detection is carried out through the acquired image data, path detection is carried out on the basis of the ground detection, and road condition detection and obstacle detection are carried out under the condition that the road is determined to be impassable to determine the obstacle avoidance reminding information so that users can quickly andsafely pass through the obstacle.

The present invention relates to a super-resolution image quality evaluation method. The method comprises: employing a pixel corresponding relation between a low-resolution image and a super-resolution image to obtain a corresponding relation between local image blocks, respectively solving the energy and the texture information of the low-resolution image and the super-resolution image, and obtaining the vision similarity between the changing of the two features. The final super-resolution image quality is obtained through evaluation of the vision similarity of the local image blocks of the low-resolution image and the super-resolution image. The experiment result shows good effects in the quality evaluation of the super-resolution image.

The invention relates to a method of machine visional detecting system that real time online detects and grades, which comprises the modules of the high-quality image obtaining, the image dynamic exchange under external trigger control and the image processing. The three modules are orderly connected by image vision data signals. The said high-quality image obtaining module includes the original image collecting module using real time screening method, Bayer conversion module decoding the collected colorful codes and Gamma correction module carrying out linear treatment to data. The said image dynamic exchange module under external trigger control through camera screening, image processing module and deleting operation of buffering area realizes the non-stop detecting to trigger interface; the said image processing module contains vision background dividing, image fast dividing and orderly storing modules. The invention can comprehensively judge the grade of each fruit and ensure the position information of every fruit and provide the judging foundations to the appearance quality online detecting of fruits.

The invention discloses a vision-based image-text defect detection method, and relates to the field of computer vision recognition. According to the method, a color high-definition industrial camera and a lens are adopted for photographing printed matters within the size, standard templates are manufactured for qualified products, feature information of the templates is extracted, and then printing samples placed in any posture are photographed and compared; according to the algorithm, high-precision multi-scale registration correction is automatically performed on sample images and template images in an image comparison process, so that complex work such as high-precision placement of a single printed matter by using a jig or manual correction of a rotation angle at present is omitted, and deformation generated by the samples in different placement postures can be automatically corrected; and finally, small image-text printing defects can be identified. Not only can characters and symbols be processed, but also various printing contents containing images, characters and forms can be processed, various defects can be better detected, and the high-standard quality detection requirements of the fields of 3C, food, medicine and the like on printed matters are met.