259 results about "Sign detection" patented technology

The invention discloses an intelligent home based old person caring device and belongs to the technical field of Internet of things. The device comprises a sign detection terminal, a fall detection terminal, a remote server and a personal mobile terminal, wherein the sign detection terminal is used for monitoring pulse, body temperature and heart rate data of a human body in real time and sending the data to the remote server; the fall detection terminal is used for monitoring acceleration, posture change and geographical position of the human body in real time, and sending alarm information and position information to the remote server and the personal mobile terminal when detecting the occurrence of fall, and a user receives falling condition information of old persons in real time through the personal mobile terminal and logging in of the remote server. The device can realize remote access, monitoring and positioning to the device user by medical staff and family members via dependence on the Internet of things about intelligent home while monitoring physical conditions and falling conditions of the old persons, and performs real-time attention on the health status of the old persons, so as to provide rescue and help in the shortest time conveniently.

The invention discloses a road warning mark detection and recognition method based on block recognition. The method comprises the following steps of performing HSV (Hue, Saturation and Value) color spatial alternation on vehicle-mounted video data and performing binarization processing; extracting profile information of a binarization image, and judging the shape of the binarization image according to the geometrical characteristics of the binarization image so as to detect a warning mark region; extracting block features and HOG (Histogram of Oriented Gradient) features of the warning mark region; matching out the type of a mark to be recognized by using a mark base as the standard; and obtaining the mark detection result. The method has the advantages that the high mark recognition correct rate can be ensured; and the missing detection is effectively reduced, so that the better mark detection result is obtained. A good application value is realized in the field of intelligent traffic.

The invention relates to the radar technology, in particular to the hidden target detection and recognition technology. The invention discloses a method for detecting a hidden living target by utilizing the radar technology and a detection device. The hidden target detection device of the invention is composed of a microwave radar, and is characterized in that the microwave radar has two different modes: a moving target detection mode and a life sign detection mode. The method and the detection device have the advantages that the detection and the positioning of the hidden target are carried out by utilizing the penetrability of the microwave. The accurate detection of the motion state of the hidden target can be carried out, the detection and the recognition of the life signs of a static target can also be carried out, thereby being able to be widely applied in fight against terrorism, disaster relief and other fields.

The invention provides a traffic sign detection method in a natural scene. The method comprises the steps that a detection image shot in the natural scene is acquired; luminance information of the detection image is subjected to statistical analysis, different luminance areas are divided according to grade luminance threshold values, pixel ratios of different luminance areas are calculated respectively, and the image is divided into a dark scene, a bright scene, a backlighting scene and a normal scene according to all the pixel ratios and scene classification threshold values; gamma parameter values are selected according to scene classification results, and an adaptive Gamma enhancement algorithm is adopted to perform image enhancement processing on a classification image; a partitioning algorithm is selected to perform image color partitioning according to different scenes in an RGB color space to obtain suspected target areas; a grayscale image obtained after color partitioning is subjected to binarization processing to obtain the suspected target areas after binarization; and the suspected target areas are screened through a feature screener to position traffic sign regions. Through the method, robustness and real-time performance of sign detection can be both considered.

A sleepiness sign detection apparatus, includes: a head movement detection unit configured to detect a head movement to generate a head movement data; an eye movement detection unit configured to detect an eye movement to generate an eye movement data; an ideal eye movement angular velocity calculation unit configured to calculate an ideal eye movement angular velocity based on the head movement data generated by the head movement detection unit; an eye-rotation angular velocity calculation unit configured to calculate an eye-rotation angular velocity based on the eye movement data generated by the eye movement detection unit; and a sleepiness sign detection unit configured to detect vestibule-ocular reflex (VOR) from the ideal eye movement angular velocity and the eye-rotation angular velocity, and determine a sign of sleepiness based on the vestibule-ocular reflex.

The present invention relates to a diabetic retinopathy sign detection method and device. The method comprises: receiving a fundus image to be detected; using a convolutional neural network (CNN) model to perform processing of the fundus image to be detected, and obtaining lesion area samples corresponding to the fundus image to be detected; according to the lesion area samples, constructing SIFT (Scale-Invariant Feature Transform) feature descriptors corresponding to the fundus image to be detected; and according to the SIFT feature descriptors, using an SVM (Support Vector Machine) classifier to determine the lesion type of the fundus image to be detected. The CNN model is employed to perform rough classification of the diabetic retinopathy to five out a lesion area, the SVM classifier is employed to perform fine classification of the lesion type of the lesion area to reduce interference generated by difference between the data size and the data when the neural network is directly configured to perform lesion classification and improve the classification precision.

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 shock protection apparatus includes a zero-gravity sensor 5 for detecting whether a hard disk drive 1 is in a zero-gravity state and accordingly generating a zero-gravity detection signal Sul; and ahead-slap sign detector 4 for outputting to the hard disk drive a signal Sul for retracting a head, if the hard disk drive 1 is determined to be in a zero-gravity state as detected by the zero-gravity detection signal Sul. In the shock protection apparatus, the influence of change over time of a shock-cushioning material is reduced, the difference in shock-resistant performance between operating and non-operating states is reduced, and signs of a head slap are detected promptly and properly to urgently retract the head.

The invention relates to a remote traffic sign detection and recognition method based on F-RCNN, which comprises: 1, preprocessing the traffic sign image sample set; 2, pre-training VGG-16 in F-RCNN;3, inputting the traffic sign training data set to the VGG-16 to complete feature extraction; 4, constructing a fusion feature map; enabling the region generation network RPN in the F-RCNN to performregion generation according to the fusion feature map to obtain a candidate region of the traffic sign; 6, inputting all candidate regions to the RoI-Pooling layer in the F-RCNN to generate a fixed-size feature vector; 7, sending the feature vector to the extreme learning machine network to output the category and location of the traffic sign; 8, training the F-RCNN model by the contribution adaptive loss function; 9, completing the traffic sign detection and identification of the actual scene. The invention realizes the detection and identification of the long-distance traffic sign, and the recognition precision is high.

The invention discloses a wearable human body multidimensional tumbling prevention and detection device and a detection method thereof. The wearable human body multidimensional tumbling prevention and detection device comprises a wearing body, a microprocessor arranged on the wearing body, a positioning module, an altitude sensor module, an ultrasound module, a movement sensing module, a sign detection module, a warning module and a display module, wherein the positioning module, the altitude sensor module, the ultrasound module, the movement sensing module, the sign detection module, the warning module and the display module are respectively electrically connected with the microprocessor. According to the wearable human body multidimensional tumbling prevention and detection device, the travelling safety of a wearer can be effectively and comprehensively predicted and prevented.

A road sign detection method comprises a scene modeling step, a color filtering step, a geometric feature filtering step, a shape detection step and an identification step, wherein in the scene modeling step, the allowed passing range of each color is determined respectively according to sample images of a plurality of scene categories; in the color filtering step, to-be-processed image scene categories are determined, and the allowed passing range of each color is utilized to filter the to-be-processed images so as to obtain respective binaryzation images of the to-be-processed images about each color; in the geometric feature filtering step, connected domain analysis is respectively performed on each binaryzation image, the geometric features of each connected domain in the binaryzation images are obtained, the connected domains with the geometric features not conforming to the road sign specifications are removed, and other connected domains are candidate road signs; in the shape detection step, the shapes of the candidate road signs are detected according to preset shapes of limited categories; and in the identification step, attributes of the candidate road signs are recognized according to the similarity level of internal characteristics and standard internal characteristics and the candidate road signs with determined shapes. A road sign detection device is further provided correspondingly.

The invention relates to a long-distance traffic sign detection and identification method suitable for a vehicle-mounted system. The method comprises the following steps: 1, preprocessing a traffic sign image sample set; 2, constructing a lightweight convolutional neural network, and completing the convolutional feature extraction of the traffic sign; 3, through a channel-spatial attention moduleembedded into the lightweight convolutional neural network, constructing an attention characteristic graph; 4, using a region generation network RPN to generate a candidate region of the target; 5, introducing context region information into the target candidate region generated by the RPN, and enhancing the mark classification characteristics; 6, sending the feature vector into a full connectionlayer, and outputting the category and position of the traffic sign; 7, establishing an attention loss function, and training an FL-CNN model; 8, repeating the steps 2-7 to complete sample training ofthe FL-CNN model; and 9, repeating 2-6 to finish traffic sign detection and identification of the actual scene. According to the invention, long-distance traffic sign detection and identification arerealized, and the precision reaches 92%.

The invention relates to a system and a method for monitoring health and registering attendance on the basis of an internet of things. The system comprises an attendance checking integral terminal. The attendance checking integral terminal is connected with a cloud monitoring server for analyzing and storing various physical examination data by a network, the cloud monitoring server is connected with handheld internet mobile equipment by a network, and the handheld internet mobile equipment is provided with monitoring and observing clients. The system and the method have the advantages that individuals who enter kindergartens or schools or nursing homes can be recognized by means of face recognition and can be photographed, various physical signs of the individuals can be detected, the various physical sign detection data can be analyzed and recorded by the cloud monitoring server which is a cloud detecting server, and can be transmitted to equipment such as mobile phones of teachers, parents, relatives or staffs on the basis of analysis and recording, and accordingly the teachers, the parents, the relatives or the staffs can see photos of the individuals and various physical sign parameters at any time; the physical sign parameters can be compared with past parameters, so that change trend of physical conditions of the individuals can be obtained, and bases can be provided for improving living and nurture environments.

The embodiment of the invention provides a danger state determination method and device, a danger warning device and a storage medium, and relates to the technical field of data detection. The methodcomprises: evaluation information used for evaluating whether a detected person is in a possible dangerous state or not is obtained, the detected person is located in a first area, and a danger warning device is located in a second area; when it is determined that the detected person is in the possible dangerous state according to the evaluation information, controlling a dangerous alarm device tocollect parameter information used for confirming whether the detected person is in the dangerous state in a first area; and determining whether the detected person is in a dangerous state based on the parameter information. The situation that the detection equipment mistakenly gives an alarm to a detected person in a dangerous state based on posture or sign detection can be effectively avoided.

The invention discloses a road sign detection method based on a region full convolution neural network. A road sign is detected using a full convolution neural network and a region recommendation network. The robustness of road sign detection is improved. The method comprises the following steps: S1, using a convolution layer to extract the features of an image; S2, using a region recommendation network to extract candidate regions; and S3, using a region-based full convolution neural network to classify the candidate regions; and S4, outputting a road sign detection result.

The invention provides a remote interaction network massage chair to overcome the technical defects that in the use process of an existing domestic intelligent massage chair, blind massage easily occurs and timely and accurate guidance is not available, and relates to the technical field of domestic intelligent massage chairs. The remote interaction network massage chair comprises a chair body, wherein a human body trunk massage unit is arranged in the chair body, leg massage units are connected to the front side of the chair body, arm massage units are arranged on armrests of the chair body, a micro-processing unit which is connected with and controls the human body truck massage unit, the leg massage units and the arm massage units is further arranged on the chair body, and the micro-processing unit is connected with a man-machine conversation unit. The remote interaction network massage chair is characterized in that the micro-processing unit is further connected with a sign detection unit and a network connection module, the sign detection unit is used for detecting sign information of a user, and the network connection module is used for being in communication connection with a network. When remote specialized guidance and analysis are conducted through the network connection module, a remote professional can timely and accurately obtain each item of sign information of the user according to the sign detection unit and make authority suggestions.

The invention provides a rescue system and a rescue method, and relates to the technical field of remote rescue. The rescue system comprises a wearable device that can be worn by a user's body, wherein the wearable device includes a sign detection unit and/or an environment detection unit, the sign detection unit is used for acquiring vital sign information of the user, and the environment detection unit is used for acquiring environmental information; a rescue decision unit, which is arranged in the wearable device or a server which is associated with the wearable device, and used for judging whether the user wearing the wearable device needs to be rescued according to the information acquired by the sign detection unit and/or the environment detection unit, and sending out a rescue signal when judging that the user needs to be rescued; and an unmanned aerial vehicle rescue device, which is in response to the above-mentioned rescue signal, and flying to the user wearing the wearable device to carry out rescue. The rescue system and the rescue method provided by the invention can effectively fight for the rescue opportunity, improve the rescue effect, and save the rescue time.

The invention belongs to the technical field of the mobile robot visual positioning, and particularly relates to a binocular full-view visual robot self-positioning method based on an SURF algorithm. The method comprises the following steps: (1) setting an artificial road sign as prior position information; (2) matching the features by the improved MDGHM-SURF; (3) eliminating the error matching by a matching point gravity center iterative algorithm; (4) ranging by the three-dimensional backlight path imaging of a vertical-base-line binocular full-view system; (5) positioning by the full-view triangle; and (6) forecasting a detection window to accelerate the positioning speed. The method is capable of, in allusion to the indoor self-positioning problem of the mobile robot, through setting the artificial road sign as the prior position information, executing the feature point rapid detection by using the improved MDGHM-SURF algorithm, executing the road sign identification positioning through the feature matching, reducing the matching error by the matching point gravity center iterative algorithm, improving the positioning accuracy of the road sign center, forecasting the road sign detection area by the robot motion state, and improving the positioning rapidity in the movement.

The invention discloses a system and a method for recognizing a railway temporary speed-limiting sign. The system comprises a video acquisition module, a video recognizing module, a control module, a display module and a voice prompting module. The video recognizing module comprises an image preprocessing submodule, a sign detection submodule, a character segmentation submodule and a character recognizing submodule. The system realizes the real-time speed-limiting sign recognition by recognizing and processing a multiframe image containing speed-limiting sign information in a video stream frame by frame and independent of single pictures, extracts a speed-limiting sign area by using an HIS space, improves the accuracy degree for recognition, further recognizes by carrying character segmentation on a yellow area and a green area, improves the speed of recognition, finally outputs a control instruction according to the recognition result, implements automatic control on the vehicle speed and simultaneously enables a driver to know the railway speed-limiting information in real time to reduce the probability of occurrence of accidents to be minimum.

The invention discloses a matrix inversion device and a matrix inversion method based on a residue number system. Conventional matrix inversion calculation based on a binary complement numerical representation system is divided into a plurality of parallel independent data channels according to a specific residue number base, so that the system complexity and the key path time delay are reduced. Therefore, a matrix inversion calculation structure based on the residue number system comprises a mapping and demapping module, a residue number system and a binary system conversion module, an n-order following matrix calculation module based on the residue number system, an n-order row and column type calculation unit and a sign detection and value zooming module for the residue number system (RNS) integer. A realizing structure based on the residue number system is designed by taking four-order positive definite Hermite matrix inversion as an example; and finally according to the definition of an inverse matrix, only a row and column type value of an original matrix and a following matrix of the original matrix are output.

The invention provides an alarm device based on face recognition and sign recognition and an alarm method. The alarm method comprises the steps that an automatic tracking camera acquires face image data, and sends the acquired face image data to a first computer; the first computer carries out characteristic comparison on the acquired face image data and face image data in a designated person library; according to a characteristic comparison result, whether the acquired face image data are the face image data of a designated person is judged, and a judgement result is sent to a second computer; a sign detection device detects whether a set sign is on the clothes of the designated person and sends a sign detection result to the second computer; and the second computer controls the alarm device to give an alarm according to the characteristic comparison result and the sign detection result.

The present invention relates to a system for vital signs detection. The system comprises a radiation source (16) for emitting radiation in a limited wavelength range for illuminating a skin area of a subject and a radiation detector (12), a radiation detector (12, 30, 40) for detecting radiation reflected from a skin area of a subject (1) in response to said illumination, and for generating first and second detector signals, the first detector signal representing radiation (2) reflected from the skin area of a subject in a first wavelength subrange of said limited wavelength range of radiation (3) and the second detector signal representing radiation in a second wavelength sub-range of said limited wavelength range of radiation different from said first wavelength sub-range, and a vital signs detector (14) for detecting a vital sign from a combination of said first and second detector signals by computing the difference between said first and second detector signals.

The failure sign detection apparatus includes an abnormality detection means to make a comparison between a failure detection parameter of a vehicle device mounted on a vehicle and a predetermined abnormality detection threshold, and make a determination whether there is an abnormality in the vehicle device based on a result of the comparison, a failure sign evaluation index calculation means to calculate a failure sign evaluation index for evaluating a sign of failure of the vehicle device based on an abnormality duration period over which the detected abnormality continues and a parameter threshold difference indicative of a difference between the abnormality detection threshold and the failure detection parameter, and a failure sign detection means to detect a sign of failure of the vehicle device based on the failure sign evaluation index calculated by the failure sign evaluation index.