46 results about "Road sign recognition" patented technology

The invention may comprise is a method and system of processing an image such as a road sign wherein the image is viewed from a host such as an automobile. The method begins with the initiating of a scan of an object to obtain an input. The input is converted to a signal before comparing the input with a set of stored inputs to determine a match. The converting step occurs via a fourier or similar transform to produce a transformed input; and, then filters the transformed input using nonlinear filtering.

The invention relates to a driving auxiliary device and a driving auxiliary method. The driving auxiliary device comprises image acquisition devices, a display, an image processing device and an alarm. Information of images around a vehicle is acquired, analyzed and processed by using a plurality of the image acquisition devices which are arranged in an optimized manner and the image processing device. On the one hand, traditional physical imaging rearview mirrors of an automobile are removed, visual blind areas of a driver are eliminated, and air resistance of the automobile is reduced; on the other hand, the acquired images are processed by the image processing device, information of risks under different driving conditions is identified, to fulfill the auxiliary functions of active safety driving, such as lane change and early warning for side impact in turning, early warning for safe interval, early warning for recognition of road signs, early warning for lane departure, early warning for pedestrian detection and collision avoidance.

The present invention includes: image capturing means (2) which captures a color image of a road via imaging means (7); area extraction means (6) which extracts areas having a similar color feature value from the captured color image of the road; white balance processing means (5) which performs, for each of the extracted areas, a white balance process of correcting each pixel data in the extracted area so as to reduce the degree of divergence in the level between color components according to a level balance between the color components of the pixel data in the extracted area; and road sign detection means (6) which detects a road sign on the road from the color image subjected to the white balance process. Thus, even if the road illumination state is partially different, it is possible to accurately detect a road sign such as a lane mark from the captured color image of the road via the imaging means such as a camera.

A driving support device detects a speed limit by imaging a speed sign indicating the speed limit of a traveling lane. Also, the driving support device continuously acquires attribute information from a car navigation system. The speed limit recognized from a road sign is displayed on a screen mounted in a vehicle. When the speed limit recognized from the road sign is not equal to a speed limit acquired from the car navigation system, a display time of the speed limit is limited. When the attribute information is changed, display of the speed limit is stopped.

The invention discloses a traffic road sign recognition method based on image saliency and depth learning. According to the method, a network (Alexnet) is generated on the basis of a convolutional neural network (CNN); traffic road sign pictures are obtained from an ImageNet data set; normalization pre-processing is performed on the training images; and the pre-processed images are inputted to the network; the Alexnet is trained; RC saliency extraction is performed on a test picture, an obtained picture is inputted into the trained Alexnet convolutional neural network; and the test classification of a traffic road sign is performed. According to the traffic road sign recognition method, a salient region can be efficiently extracted based on image saliency, and the advantages of depth learning in picture recognition are utilized in combination, and therefore, the traffic road sign can be accurately classified.

A driving support device detects a speed limit by imaging a speed sign indicating the speed limit of a traveling lane. Also, the driving support device continuously acquires attribute information from a car navigation system. The speed limit recognized from a road sign is displayed on a screen mounted in a vehicle. When the speed limit recognized from the road sign is not equal to a speed limit acquired from the car navigation system, a display time of the speed limit is limited. When the attribute information is changed, display of the speed limit is stopped.

Vehicles can be equipped with computing devices, networks, sensors and controllers to determine, modify, and / or augment a digital map of the surrounding real world. Computing devices included in a vehicle can determine road sign locations in LIDAR data. The computing devices can identify the road signs in one or more video images based on the road sign locations and include the road signs in the digital map based on the road sign identity and the road sign location.

The embodiment of the invention discloses a road sign recognition method and device, a medium and a terminal, and the method can comprise the steps: obtaining a three-dimensional point cloud data setwhich comprises a plurality of three-dimensional point cloud data points obtained through the detection of a road; mapping the three-dimensional point cloud data set into a two-dimensional plane image; adopting a machine learning model to identify a road sign in the two-dimensional plane image; and inversely mapping the road sign in the two-dimensional plane image to a three-dimensional coordinateposition. The technical scheme in the embodiment of the invention is higher in accuracy.

A vehicle and road sign recognition device each includes: image capturing means (2) which captures a color image of a road via imaging means (6); feature value calculation means (4) which calculates a feature value of each pixel corresponding to the color of a road sign on the road from the color components of each pixel in the color image so as to reduce the effect of brightness on the color components; and road sign detection means (5) which detects the road sign on the road from the feature image in which the feature value of each pixel in the color image is arranged so as to match with the position of each pixel in the color image. Thus, it is possible to accurately detect a road sign such as a lane mark from the color image of the road captured via the imaging means such as a camera even if the road illumination state is partially different.

Disclosed are a road surface marker recognition device and a method. The device includes an infrared transceiver that is configured to irradiate an infrared beam on a road surface and receive the reflected beam to detect a distance from a road surface and the strength of the reflected beam. The device further includes a controller that is configured to create a road map of the road using distance information, signal strength information, and speed information of a vehicle so as to define a marker shape of the road. Furthermore, the controller is configured to compare the defined marker shape with stored marker information to determine a definition of the marker shape and output the marker shape definition.

The present invention includes: image capturing means (2) which captures a color image of a road via imaging means (7); area extraction means (3) which extracts areas having a similar color feature value from the captured color image of the road; white balance processing means (5) which performs, for each of the extracted areas, a white balance process of correcting each pixel data in the extracted area so as to reduce the degree of divergence in the level between color components according to a level balance between the color components of the pixel data in the extracted area; and road sign detection means (6) which detects a road sign on the road from the color image subjected to the white balance process. Thus, even if the road illumination state is partially different, it is possible to accurately detect a road sign such as a lane mark from the captured color image of the road via the imaging means such as a camera.

A vehicle and road sign recognition device each includes: image capturing means (2) which captures a color image of a road via imaging means (6); feature value calculation means (4) which calculates a feature value of each pixel corresponding to the color of a road sign on the road from the color components of each pixel in the color image so as to reduce the effect of brightness on the color components; and road sign detection means (5) which detects the road sign on the road from the feature image in which the feature value of each pixel in the color image is arranged so as to match with the position of each pixel in the color image. Thus, it is possible to accurately detect a road sign such as a lane mark from the color image of the road captured via the imaging means such as a camera even if the road illumination state is partially different.

The invention discloses a road sign recognition system and method. The road sign recognition system comprises a road sign recognition device and a server, wherein the road sign recognition device comprises a control module, a display module, a human-machine interaction module, a computer mode recognition module, a memory module, an image fusion module and a communication module, wherein the display module, the human-machine interaction module, the computer mode recognition module, the memory module, the image fusion module and the communication module are respectively connected with the control module, and the communication module is connected with the server through a wireless network. When the road sign recognition system and method are adopted, characters in an actual road sign can be translated according to a languish set by a user, the translated characters are fused in an image of the road sign to be displayed, therefore the defect of markup information of the road sign due to languish barrier is overcome.

The invention discloses a road sign recognition method based on a conditional random field, and mainly solves the problem of low recognition accuracy of an existing road sign. The implementation scheme of the road sign recognition method based on conditional random field comprises the following steps of: 1. establishing a set of road sign color seed points according to pure road sign image data; 2. calculating a set of a priori color feature diagrams of images containing the road sign according to the set of road sign color seed points; 3.calculating a set of color probability distribution diagrams of images containing road sign by Bayesian Decision Theory; 4. combining the prior color feature diagram and the color probability distribution diagram of the road sign image with Markov conditional random field model to obtain a combined image; 5. extracting a region of interest in the combined image; and 6. classifying and recognizing the region of interest through a multi-scale convolutional neural network. According to the road sign recognition method based on conditional random field, the detection rate of the road sign and the recognition accuracy of the road sign are improved; andthe method can be used for scene perception in the traffic field.

A method of automatically preventing or reducing aquaplaning during the driving operation of a motor vehicle on a route provides that:a) a camera-based road sign recognition of a road sign on a section of the route determines whether the road sign indicates a risk of aquaplaning on the section of the route,b) at least one sensor device detects whether there is a wet road condition on the section of the route, andc) a driving assistance function for preventing or reducing aquaplaning is carried out if the road sign recognition determines that the road sign indicates the risk of aquaplaning and the sensor device detects the wet road condition on the section of the route.

A road sign recognition apparatus generates a mosaic image formed by connecting accumulated images from a camera in time-series order, determines multiple road signs contained in the mosaic image by template matching, and generates positional information for the use of knowing a relative position of a vehicle to the road sign.

The invention provides a road sign recognition method and device and electronic equipment, and relates to the technical field of image processing. According to the scheme, the method comprises: inputting an obtained to-be-detected image into a pre-trained road sign recognition model, so as to carry out the road sign recognition of the to-be-detected image, wherein the road sign recognition model is obtained by training based on a sample image set (the sample image set contains a sample image with an interference item), so that the road sign recognition model can effectively eliminate the interference item in the image and learn the road sign in the image foreground. Therefore, when the road sign recognition model is used for recognizing the to-be-detected image, the road sign in the imagecan be effectively recognized under the condition that interference items exist, and the accuracy of road sign detection is improved.

A method combines a road sign recognition system and a lane detection system of a motor vehicle. The road sign recognition system generates road sign information from sensor data of a camera-based or video-based sensor system and the lane detection system generates lane course information from the sensor data. Meaning-indicating data for road signs are generated from the lane course information, and are used to check the plausibility of and / or to interpret the road sign information. Data indicating the course of the lane are generated from the road sign information, and are used to check the plausibility of and / or to interpret the lane course information.

The invention adopts a characteristic extracting technology of a local characteristic matching technology and performs characteristic matching by using a method combining characteristic extraction and binary characteristic description based on a curvature in accordance with road sign matching scene application requirements of outdoor scenes. An algorithm utilizes reasonable characteristic of characteristic distribution based on a curvature algorithm and solves the problem that the distribution of characteristics is uneven, the defect that the real-time capability of other algorithms is weaker is overcome through the binary description algorithm, and finally the validity and the real-time capability of the algorithm are contrasted through experiments. Results indicate that the algorithm can ensure the real-time capability, at the same time, effective even characteristic points are extracted, and the algorithm has better practicality and robustness.

The invention provides a road sign recognition method, system and device, and the method comprises the steps: collecting pictures of a road sign in different environments, and storing the pictures ina data set; utilizing the data set to create a convolutional neural network model; utilizing the convolutional neural network model to extract feature vectors of road sign pictures in a data set, andstoring the extracted feature vectors into a feature vector set; training a top-speed learning machine model by utilizing the feature vector set; and using the convolutional neural network model and the extreme learning machine model as a combined model to identify a road sign picture to be identified. According to the invention, the road signs in various visual field environments can be accurately recognized, the recognition result is broadcasted through voice, the driving safety is improved, and meanwhile, technical support is provided for unmanned driving.

A technique, which makes it possible to estimate a curve shape of a road more simply and more accurately, is provided. Disclosed is a road shape estimating system for estimating the shape of the road including a curve easement section in which a radius of curvature changes according to a clothoid curve and a circular curve section in which a radius of curvature is constant. The distance Lp from a curve starting point and the radius of curvature Rp of the curve at a vehicle position in the curve easement section, are determined on the basis of the information from a white line recognition camera of the vehicle, a yaw rate sensor and a wheel speed sensor, and the radius of curvature Rreal of the circular curve section is determined from an image of a road sign recognition camera. Then, the length Lclo of the curve easement section is derived by using the information as described above and a clothoid function to estimate the shape of the road.

The invention provides a road sign arrangement optimizing method and a corresponding robot positioning method. Road sign arrangement in the environment is optimized. Each positioning basic unit is formed through a plurality of road signs. All the positioning basic units in the overall environment form a road sign map. Difference degrees are defined. The road sign arrangement is optimized to make the difference degrees maximum, thus increasing reliability of map matching and increasing reliability of robot positioning. In the positioning method, sensors detect the road signs, match with the road sign map, and determine positions of robots after success matching. The road sign arrangement optimizing method and the corresponding robot positioning method are advantaged by easy road sign recognition, high reliability of map matching, high reliability of positioning, wide applications, and the like.

The invention provides a road sign and a device used for determining the position of a robot, wherein the road sign consists of one or more labels with different functions; each label consists of one or more signs; materials capable of absorbing ultrasonic waves are coated on the labels or the signs are made of the materials. According to the road sign provided by the invention, ultrasonic waves are applied to the road sign for determining the position of the robot, so that the ultrasonic wave radiation range is wide; the ultrasonic waves generated by the device provided by the invention can be radiated to the road sign and other objects of a space where the robot is located, so that all labels of the space where the robot is located can be detected once. The road sign is free of light interference and is high in recognition precision, so that road sign recognition efficiency is greatly improved.

The invention relates to the field of traffic information service, and provides a new road discovery method and device, equipment and a storage medium. The new road discovery method comprises the steps: collecting new information data in advance, judging whether a vehicle is near a new road information place by analyzing a positioning point of vehicle-mounted equipment carried on the vehicle; whenthe vehicle is near a new road information place, matching the recent track of the vehicle with the existing road network data; taking a part, which cannot be matched with the existing road network,in the track as a suspected new road; and further calling the video data of the vehicle-mounted equipment, and verifying whether the suspected new road is the new road through the road sign recognition and matching technology. Therefore, the new road discovery method can obviously improve the new road information collection and verification efficiency, can accelerate the map product updating progress, does not need collection team field investigation, and reduces the information collection cost.

The invention relates to a road traffic sign automatic identification and classification method. The method comprises the following steps: S1, collecting a road image by using a vehicle-mounted imagecollection device; s2, screening and marking images with traffic signs out from the collected road images, and constructing a data set required by Mask _ RCNN model training; s3, inputting the data set obtained in the step S2 into a Mask _ RCNN model for training to obtain a trained weight; s4, performing road sign recognition and classification on all the acquired road images by using the weighttrained in the step S3; s5, checking the generated result, carrying out the secondary marking of the image with a poor recognition effect, and training the weight again; s6, outputting an identification result. The method is beneficial to improving the recognition and classification effects of the road traffic signs.

The invention is based on a machine vision early warning system and method for driving in fog and missing road signs, and belongs to the technical field of intelligent vehicle safety assisted driving. The present invention constructs a real-time road sign recognition early warning strategy by means of a road traffic sign recognition classifier, a road traffic sign character classification recognition neuron network classifier, a driver fatigue pattern classifier, a fog-free image classifier, and an image defogging model . According to the driver's gaze trajectory, blink frequency, and PERCLOS value, if it is judged that the driver is fatigued or misses traffic sign information due to performing secondary tasks during driving, the car speaker will issue a sound warning of real-time sign information and display it on the car display. Display the warning sign information, and if it is judged to be foggy, it will also provide the driver with visual and auditory warnings, so that the driver can obtain road traffic sign information and driving safety warnings under the conditions of foggy weather and drivers missing road signs .

In an apparatus for assisting a driver of a vehicle in driving the vehicle, a road sign recognizer is configured to recognize a road sign from an image captured by a vehicle-mounted imager. A turn detector is configured to detect a turning action of the vehicle. A notifier is configured to notify the driver of the vehicle of road sign information representing the road sign recognized by the road sign recognizer. The notifier is further configured to, if the turning action of the vehicle is detected by the turn detector, withhold notifying the driver of the vehicle of the road sign information representing the road sign recognized by the road sign recognizer within a predetermined period of time during the turning action.

The embodiment of the invention relates to the technical field of vehicle intelligent auxiliary driving, and discloses a track road sign recognition method and system. The method comprises the steps of obtaining the moving characteristics of a vehicle during a parking process, and extracting the key characteristics from the moving characteristics through a plurality of sliding windows; calculating the recognition credibility of a target track road sign corresponding to the key characteristic at the junction of the sliding window according to the key characteristic; determining an optimal target track road sign from the target track road signs according to the identification credibility; and obtaining the road sign information of the optimal target track road sign, and associating the road sign information with a position corresponding to the optimal target track road sign in the track map. By implementing the embodiment of the invention, the track road sign can be identified, the track road sign is combined with the track map, and the safety and comfort of the autonomous parking are improved.