323 results about "Person detection" patented technology

Systems and methods are provided for machine learning based monitoring. Image data from a camera is received. On the hardware accelerator, a person detection model based on the image data is invoked. The person detection model outputs first classification result. Based on the first classification result, a person is detected. Second image data is received from the camera. In response to detecting the person, a fall detection model is invoked on the hardware accelerator based on the second image data. The fall detection model outputs a second classification result. A potential fall based on the second classification result is detected. An alert is provided in response to detecting the potential fall.

Disclosed in the present application is a skeleton detection and fall detection method based on improved spatio-temporal adaptive graph convolution. The method comprises the steps of: S1, collecting image data to acquire data of each image frame; S2: using a pre-trained yolov5 target person detection model to detect whether a target person is present in the data of each image frame, and if a target person is present, turning to step S3, and if no target person is present, ending the process; S3: for each detected target person, using a Deepsort target tracking algorithm to perform target tracking to obtain a tracking result, calculating the similarity to obtain the result of target association, and updating trajectory information of each target person; and S4: performing pose recognition on each target person on the basis of the trajectory information, using a spatio-temporal adaptive graph convolutional network to extract a feature vector of a pose, and using a classifier to perform human body behavior classification and recognition, in order to determine whether the target person has experienced a fall incident. The method achieves higher accuracy and robustness.

The invention discloses an interactive action detection method based on multi-level features, and the method comprises the steps: S1, fusing the information of a low-level feature map, a middle-level feature map and a high-level feature map through a cascading fusion mode, and obtaining a fused feature map; s2, acquiring local detail features from the fused feature map, performing global modeling to obtain global features, fusing the global features with the local detail features to generate global context features, performing character detection, object detection and interaction detection in parallel through multi-task branches, outputting character features, object features and interaction features, and outputting the character features, the object features and the interaction features. S3, gradually fusing multi-level contexts through attention interaction of a unitary relationship, a pairwise relationship and a ternary relationship, generating text embedding for an interaction category by utilizing a pre-training text encoder, and aligning the text embedding with visual features to improve the accuracy of fine-grained interaction classification; and S4, explicitly modeling a complex interaction relationship, and finally predicting and outputting a final prediction result by using FFN.

The invention relates to the technical field of artificial intelligence computer vision, in particular to an event camera pedestrian detection method based on a space-time state space model, and the method comprises the steps: collecting a pedestrian detection data set based on an event camera, obtaining original event data, carrying out the preprocessing, determining an event tensor, and obtaining an event frame sequence; modeling is carried out through combination of a state space and an event tensor, an event-driven recursive space-time state space module is defined as a core unit, and an isomorphic deep neural network architecture is constructed; training the isomorphic deep neural network architecture by adopting the training set, and verifying through the verification set; inputting the test set into the verified isomorphic deep neural network architecture for detection, and generating a pedestrian detection result; the collaborative optimization of sparse adaptation-dynamic capture-noise suppression is realized in a unified framework, the essential characteristics of the event camera triggered based on brightness change are theoretically fit, and higher robustness and generalization ability are shown in an actual complex scene.

The invention discloses a multi-view child motion coordination ability evaluation system and method based on deep learning, belongs to the technical field of motion evaluation, and solves the problems that child motion evaluation in the prior art mainly depends on manual observation and simple physical testing, and multiple angles and key details of child actions are difficult to synchronously track. The method comprises the following steps: training to obtain a skeleton point detection model and an athletic ability evaluation model, acquiring real-time video streams of personnel entering a field based on an acquisition camera, identifying skeleton key points in a preprocessing data set by the skeleton point detection model, performing multi-person detection on a personnel matching result based on an athletic area division method, and evaluating the athletic ability of the personnel. The exercise ability evaluation model carries out quantitative analysis on multi-person detection results; according to the invention, visual identification and motion state detection technologies are combined, a front view angle and side view angle dual-camera layout is adopted, and a deep learning algorithm is matched, so that automatic children dynamic motion evaluation is realized. The action process can be completely captured, and the detection accuracy and efficiency are improved.

The invention discloses a roadway cleaning robot autonomous navigation and operation system based on multi-sensor fusion. The roadway cleaning robot autonomous navigation and operation system comprises a mechanical system, a control system and a power system. The mechanical system comprises a crawler chassis, a mechanical arm and a big arm turntable; the control system software part presentation layer comprises a user interaction and management module, the business layer comprises a task planning and decision module, and the function layer comprises a robot autonomous walking control module, a roadway deformation detection module, a mechanical arm accessory replacement control module and a mechanical arm roadway cleaning control module. The sensing layer comprises an infrared person detection module, a laser radar mapping positioning module, a mechanical arm visual positioning module and a mechanical arm state feedback calculation module; the hardware part comprises a laser radar, an IMU, a sensor and the like. Various sensor data are fused, accurate positioning, autonomous walking, mechanical arm visual positioning, roadway deformation detection, accessory automatic replacement, roadway automatic cleaning and the like of the robot are achieved, and the intelligent level and the working efficiency of the robot are improved.

The invention relates to a target person detection method and device based on millimeter wave radar, equipment and a medium. According to the method, radar detection configuration is adjusted, a gridding coordinate system is established in a target treadmill monitoring area, millimeter wave radar is used for collecting feature data related to movement of a target person, and movement track changes of the target person are extracted to generate person position information; acquiring breathing and heartbeat signals of a target person, and performing signal filtering and feature extraction to obtain vital sign information; comprehensively evaluating the existence state of the target person according to a preset threshold value and a discrimination standard in combination with the person position information and the vital sign information; and when the evaluation result shows that the target person leaves, the vital signs are abnormal or a cheating behavior exists, judging that the target person is in an abnormal state, and generating a corresponding early warning instruction. By adopting the method, abnormal conditions can be found in time, early warning can be generated, and the monitoring accuracy and response speed are improved.

The invention relates to a dense pedestrian detection method for a traffic scene, and belongs to the technical field of machine vision, and the method comprises the following steps: S1, collecting pedestrian images of the traffic scene, and constructing a training and testing data set; s2, constructing a pedestrian detection network, fusing high and low frequency attention and a bidirectional feature fusion module, and introducing a target frame matching strategy; s3, preprocessing the image, and inputting the preprocessed image into a detection network training model; and S4, deploying the trained model to a traffic monitoring system to realize pedestrian detection. The method improves the detection precision and the calculation efficiency, still has the precise detection capability in a complex background and a dense shielding environment, and can be applied to an intelligent traffic monitoring and automatic driving system.

The invention belongs to the field of machine learning and target detection, and discloses an infrared and visible light fusion pedestrian detection method based on weight autonomous optimization. According to the method, feature extraction is carried out on infrared and visible light images through a convolutional neural network; and through a learnable proportionality coefficient, the extracted features are superposed back to the original image according to respective proportions. In the feature fusion stage, the fusion proportion of the infrared and visible light modes is dynamically adjusted through a learnable fusion weight coefficient. In the training stage, end-to-end optimization is carried out by using a large-scale annotation data set, so that the superposition proportion and the fusion weight alpha of each mode can be adaptively adjusted to adapt to different illumination conditions and scene changes, and the generalization ability of the model is remarkably improved. In a robot vision system for night pedestrian detection, an infrared and visible light modal fusion method based on machine learning weight optimization is adopted, and the accuracy and robustness of pedestrian detection are effectively improved.

A smart doorbell, for a security system, which is capable of performing functions including, person detection, facial recognition, motion detection, detection of baby or pet running away, weapon detection, fire detection, detection of parcel left at porch, parcel theft, dog poop detection, vehicle detection, animal detection, eavesdropper detection, a person jumping from backyard wall, and intruder detection. The functions are detected through a camera of the doorbell and, subsequently, AI-based alerts are generated.

The invention discloses a multi-pedestrian target detection method based on a YOLOCDG network in a complex scene, and aims to solve the problems of small target missing detection, model redundancy and inaccurate positioning in multi-pedestrian detection in a scene with dense people flow and serious shielding. The method comprises the following steps: firstly, based on YOLOv8, deleting a redundant convolution fusion layer of a backbone network, adjusting the size of a detection head, and simplifying a framework to reduce small target feature dilution; secondly, designing a context attention module CoAM and embedding the CoAM into a backbone network, and enhancing feature distinction degree in a shielding scene by capturing cross-target context association of dense pedestrians; thirdly, an improved C2fG module is proposed to replace a neck C2f module, the parameter quantity is reduced, and the detection performance and the edge deployment efficiency in a complex scene are balanced; then, an SPPFDSC multi-scale fusion layer containing depth separable convolution is designed, an original SPPF layer is replaced, and fine-grained feature perception of small-size pedestrians in the distance is enhanced; and finally, optimizing a bounding box loss function by adopting WIOU v3, improving the target positioning precision in the dense people stream, and finally constructing a multi-pedestrian detection model.

The invention relates to the technical field of image processing and target tracking, in particular to a cross-view fusion multi-person detection and tracking method for outdoor view variety, which comprises the following steps of: reconstructing a multi-view picture into three-dimensional / BEV space priori under a unified world coordinate, and feeding back the priori to each camera position feature by using space enhancement attention to obtain a consistent and steady multi-person detection result; then, carrying out online iteration updating on the three-dimensional position and posture of the figure in a tracking mode, introducing OKS-3D gating to combine the 2D key point consistency with the BEV spatial distance, and keeping a uniform ID and a continuous track across cameras; the method solves the problem that the prior art cannot effectively meet the requirements of real-time, accurate and stable target detection, tracking and identity association of an outdoor variety in a complex shooting environment, realizes time-space structured output of accurate detection, stable tracking, unified ID and visual positioning, can directly serve for director scheduling and post-production, and is high in practicability. And the overall manufacturing level and quality of the exterior variety are improved.

The invention provides a target detection method and system and a storage medium, and relates to the field of object detection, and the method comprises the steps: obtaining image data and laser radar scanning data corresponding to a current scene; calling a first pedestrian detection model based on an image to carry out pedestrian detection on the image data to obtain position information of a pedestrian target; calling a second pedestrian detection model based on point cloud data to carry out pedestrian detection on the laser radar scanning data to obtain pose information of a pedestrian target; and calling an external parameter matrix to match the position information and the pose information, and outputting three-dimensional position information of the pedestrian target in a space coordinate system. According to the invention, the detection and positioning of the pedestrian target can be realized without using a high-cost depth camera and a three-dimensional laser radar, and the detection precision of the pedestrian target is improved through two different modal data.

The invention discloses a long-distance identity recognition method for a large area, which belongs to the technical field of computer vision and comprises the following steps: S1, initializing a system; s2, collecting video data; s3, pedestrian detection and segmentation; s4, performing gait recognition; s5, multi-target cross-camera tracking is carried out; and S6, result output and application service. According to the invention, an effective solution is provided for large-scene video intelligent security and protection in a complex environment of a park, the accuracy and traceability of personnel identity recognition in a high-risk area are ensured, and the safety production level of the park is improved; a long-distance multi-target identity recognition scheme is provided, real-time monitoring and early warning of illegal person invasion in key protection areas are achieved, and reliable safety guarantee is provided for public places.

The embodiment of the invention discloses a people counting method and device based on an image full scene, equipment and a medium. The method comprises the following steps: detecting a to-be-detected image to obtain an initial head and shoulder frame and a whole person frame in a whole scene of the image; a head and shoulder frame corresponding to the whole person frame is obtained according to the whole person frame and serves as a whole person head and shoulder frame; according to a matching result of the initial head-shoulder frame and the whole-person head-shoulder frame, screening a target head-shoulder frame, and according to the screened initial head-shoulder frame and the whole-person head-shoulder frame, determining a people counting result; wherein the target head and shoulder frame comprises an initial head and shoulder frame or a whole head and shoulder frame. According to the technical scheme, the whole person frame is converted into the whole person head and shoulder frame, the size difference between the whole person detection frame and the head and shoulder detection frame is reduced, and the accuracy of people counting can be improved based on multi-label matching.

The invention provides a personnel detection method, equipment and a program product, personnel are detected based on a top-mounted camera, and the method comprises the following steps: a target detection network structure receives a plurality of continuous video frames; for each frame, the target detection network structure identifies whether the target person has a predetermined label pattern in a predetermined body area, and counts the total number of frames having the predetermined label pattern; if the total frame number is greater than a preset number threshold value, determining that the target person is a person meeting a preset attribute; otherwise, determining that the target person is a person which does not meet the predetermined attribute; the number threshold is less than a predetermined number and greater than or equal to 2; wherein the target detection network structure is an improved network structure based on YOLO-V5; wherein the YOLOv8 network structure C2f is used for replacing C3 in the YOLO-V5 network structure, the SSPF of the YOLO-V5 network structure is improved into the SSPFM, and the CBAM module of the YOLO-V5 network structure is improved into the CBAMLSA. By means of the technical scheme, the personnel meeting the preset attributes can be accurately recognized in the scene of the top-mounted camera.

The invention discloses a light-weight unmanned forklift AI visual anti-collision method based on a domestic embedded platform, and the method comprises the following steps: S1, carrying out the preprocessing of an RGB image through a light-weight pedestrian detection module, carrying out the automatic pruning and compression of a deep convolutional network based on an image recognition algorithm of a light-weight convolutional neural network, and carrying out the recognition of the deep convolutional network; lightweight pedestrian detection features are extracted; s2, using a lightweight pedestrian distance estimation module to extract lightweight pedestrian distance estimation features by model compression through camera calibration, image correction, stereo matching and distance acquisition; s3, performing feature fusion, performing feature analysis in combination with a dynamic adaptive sparse transformation network, and completing multi-pedestrian detection and pedestrian distance estimation by introducing a sparse feature adaptive reconstruction mechanism; and S4, deployment is carried out on a domestic embedded platform, and software function module cutting is carried out. According to the invention, a lightweight deep learning algorithm and adaptive feature fusion are adopted, and multi-pedestrian anti-collision detection on a domestic embedded platform is realized.

The invention belongs to the technical field of intelligent traffic and computer vision crossing, and particularly relates to a pedestrian detection method based on multispectral fusion. Aiming at the bottleneck problem that single-source data sensing reliability is insufficient in a complex traffic scene, the invention provides a visible light-infrared double-flow collaborative pedestrian detection framework based on a neural network. According to the method, complementary semantic information between visible light and infrared images is fully mined, a multispectral feature dynamic interaction mechanism composed of three stages of feature decoupling, interaction and reconstruction is established, and robust multispectral representation is generated through a feature fusion module based on channel attention. Compared with an existing method, the method has the advantages that target feature discrimination can be remarkably improved, higher adaptability is achieved in multi-scene, multi-scale and multi-target detection tasks, accurate positioning and recognition of pedestrian targets in the all-weather environment can be achieved, and reliable technical guarantee is provided for an intelligent traffic monitoring system.

The invention relates to the technical field of computers, and provides a cloud-edge collaborative abnormal behavior character recognition method, device and system, and the method comprises the steps: edge end equipment employs a trained pedestrian detection model to cut out a video sequence containing pedestrians from a received video sequence, and uploads the video sequence containing the pedestrians to a cloud server; the cloud server cuts a video sequence containing pedestrians according to a set time length to obtain video slices, the video slices and prompt words are input into a trained multi-mode large model to obtain an identification result, the prompt words are described in a video question and answer mode, option question and answer pairs in video question and answer are constructed according to related task types, and the identification result is obtained. The options in the video questions and answers are possible behavior types. The lightweight pedestrian detection is integrated on the side end equipment to reduce the transmission, reduce the processing data volume of the cloud server, solve the problem of high demand of cloud computing resources, and improve the efficiency and response speed of the system.

The various embodiments described herein include methods, devices, and systems for providing event alerts. In one aspect, a method includes obtaining a video feed. A frame of the video feed is analyzed at a first resolution to determine whether the frame includes a potential instance of a person. In accordance with the determination that the image includes the potential instance, a region is denoted around the potential instance. The region is analyzed at a second resolution, greater than the first resolution. In accordance with a determination that the region includes the instance of the person. a determination that the frame includes the person is made. An indication of the determination is stored for use in subsequent alert notification processing.

The invention discloses a super-realistic digital human detection method based on motion modeling, and the method comprises the steps: carrying out the motion sequence extraction of a designated person based on a human body three-dimensional model; extracting motion features of the specified character based on the motion sequence and a visual model; and for the extracted motion features, mapping the motion features into a feature space, constructing an action feature distribution hybrid model, calculating an abnormal score of the digital human under normal feature distribution based on the model, and completing digital human counterfeiting detection according to the abnormal score. According to the method and the system, a super-realistic digital human forgery detection method based on action modeling is matched with an existing action capture technology, more universal action characteristics can be learned, so that the effect of detecting the super-realistic digital human is achieved, and the method and the system have relatively high generalization.

The invention relates to the technical field of robot detection, and discloses a Delta mechanical arm precision detection method, system and device and a storage medium, and the Delta mechanical arm precision detection method comprises the steps that multiple actual position coordinates of the tail end of a mechanical arm in the movement process along a preset track are obtained according to a selected detection mode; geometric fitting is carried out based on the actual position coordinates, and corresponding circle center coordinates are determined; the tail end is controlled to move to the circle center coordinates, and actual position coordinates at the moment are obtained; and error information representing an absolute precision error is generated based on a difference value between the position and the circle center coordinate. According to the method, automatic detection of the absolute positioning precision of the manipulator is achieved, and error quantization can be completed without depending on external measuring equipment; the generated error vector accurately reflects the direction and size of system deviation, compensation and correction are facilitated, and the method has the advantages of being high in detection efficiency, reliable in result and high in applicability.

The invention relates to a lightweight pedestrian detection algorithm based on improved YOLOv7-tiny, and the algorithm comprises the steps: replacing an ELAN module with an ELCG module on the basis of an original YOLOv7-tiny network to carry out the feature extraction of an input image, and carrying out the feature enhancement in a feature fusion sub-network through employing an ECA attention mechanism; comprising the following steps: obtaining a pedestrian detection picture, and shortening the picture processing time and constructing a data set D1 by using a data enhancement and adaptive size scaling method; an improved YOLOv7-tiny model is constructed; the data set D1 is input into the improved YOLOv7-tiny model to be trained; and pedestrian detection is carried out on the trained improved YOLOv7-tiny model, loss function calculation is carried out on a detection result and a sample label, and parameters in the model are optimized through a gradient descent algorithm and a back propagation algorithm. According to the lightweight pedestrian detection algorithm based on the improved YOLOv7-tiny, an ECA attention mechanism is introduced, and the network structure is improved, so that the detection precision of pedestrians in a complex environment is improved, and the accuracy of capturing and identifying features in pedestrian detection is improved.

The invention provides a multi-view pedestrian detection method and system based on dual adaptive feature fusion, and belongs to the technical field of computer vision. According to the method, in a unified aerial view space, firstly, a cross-view feature selection module is introduced, and a multi-head self-attention mechanism is utilized to perform dynamic complementation and weighted fusion on features from different cameras so as to enhance the semantic integrity of a shielded area; then, a view channel map attention module is introduced, fused features are constructed into a view-channel map structure, modeling is carried out on the joint dependency relationship between view channels through a map attention perception multilayer perceptron combining global and local context pooling, self-adaptive reweighting of channel importance is achieved, and the self-adaptive reweighting of channel importance is realized; therefore, the discrimination of the fusion features is improved. And the finally obtained unified features are used for ground pedestrian positioning. According to the method, the detection performance bottleneck caused by visual angle shielding and channel redundancy is effectively relieved, and the quality of the ground occupancy map is remarkably improved.

The invention discloses a pedestrian multi-target tracking method based on an attention mechanism, and the method comprises the steps: inputting a current frame image into a trained target tracking model: inputting the current frame image into a backbone network for feature extraction, and obtaining pedestrian feature maps of multiple scales; inputting the pedestrian feature maps of multiple scales into a target sensing module for weighted fusion to obtain a fused feature map; inputting the fused feature map into a feature decoupling module for feature decoupling to obtain a first feature map for target detection and a second feature map for Re-ID; respectively inputting the first feature map and the second feature map into a target detection branch and an Re-ID branch to carry out target detection and Re-ID; and the secondary association algorithm realizes association matching of the pedestrian detection frame and the trajectory based on the detection result and the appearance embedding vector to obtain the tracking result of each target. According to the invention, the accuracy and effectiveness of pedestrian multi-target tracking can be improved.

The invention discloses a vehicle violation manned intelligent detection method and system based on a CLIP and D-Fine cascade framework, and the method comprises the steps: collecting a real-time video frame image of a preset traffic monitoring network, processing the real-time video frame image, inputting a monitoring image into a CLIP-ILP model, employing the CLIP-ILP model as a filter, and combining with a Top-K screening strategy, and screening out candidate images; and inputting the candidate image into a constructed context enhanced D-FINE detection model, carrying out positioning and multi-class detection on a preset target, outputting a multi-class detection result, and executing verification of a spatial co-occurrence rule, a license plate position heuristic rule, a size consistency rule and a context consistency rule. And marking the result which does not pass the verification as suspicious or rejecting the result, and outputting the result which passes the verification as an illegal manned detection result to the target terminal. According to the method, the problem of balance between the recall rate and the precision in manned detection can be solved.

The invention discloses a library people flow monitoring method and system based on multi-mode and trajectory fusion. The method comprises the steps of collecting a video stream, generating a weight image by using an attention mechanism to enhance a pedestrian area, extracting a pedestrian frame through YOLOv11 target detection, and positioning a pedestrian subject and separating a background in combination with a segmentation model; feature points and descriptors are extracted through SuperPoint, inter-frame motion parameters are calculated through feature matching, and tracks are predicted and verified by means of Kalman filtering; and finally, associating pedestrian tracks through unique IDs, and dynamically tracking in and out states to count the pedestrian flow. According to the method, the problems of shielding, small target missing detection and track drifting are effectively solved, and high-precision people flow statistics is realized; more accurate and robust pedestrian detection and tracking are realized through multi-modal data fusion and dynamic trajectory fusion; through the schemes of feature point extraction, Kalman filtering and the like, the prediction of pedestrian motion trails is optimized, and the real-time performance and precision of pedestrian flow monitoring are improved.

The invention relates to the technical field of pedestrian trace alarm, in particular to a pedestrian trace detection alarm method and system based on image recognition, and the method comprises the steps: matching the real-time image data of a pedestrian detection region with the feature image data of people in the pedestrian detection region, and generating the recognition data of people in the pedestrian detection region; when the person identification data in the pedestrian detection area indicates that pedestrians exist, real-time image feature data of the persons in the pedestrian detection area are collected, pedestrian position coordinate analysis processing is carried out, and real-time position coordinate data of the persons in the pedestrian detection area are generated; and matching the real-time position coordinate data of the personnel in the pedestrian detection area with the safety activity range data of the pedestrian detection area, if a matching result feeds back that the pedestrian position is abnormal, constructing pedestrian trace detection alarm data, and pushing the pedestrian trace detection alarm data to a pedestrian trace detection alarm Internet of Things platform through an Internet of Things communication network. Accurate detection of pedestrian traces and timely early warning when abnormity occurs are realized.

The invention discloses a coal preparation plant production personnel positioning method and system based on video analysis, and the method comprises the steps: processing a video stream through employing an improved OfficientDet model, and obtaining an initial target personnel detection frame; processing the initial target person detection frame by using an improved FairMOT model and a dynamic motion model to obtain a continuous tracking trajectory of the target person; processing the continuous tracking trajectory of the target person by using a multiple linear regression model, predicting the position of the next frame, and allocating weights by using an entropy weight method to obtain a predicted motion trajectory; and processing the continuous tracking trajectory of the target person by using a ResNet-50 model to obtain a depth feature, performing identity confirmation of the target person based on the feature, and associating the identity with the predicted motion trajectory to complete person positioning. According to the method, tracking errors caused by environmental changes are reduced, and effective application in different environments is ensured.

Methods and systems for identifying persons utilizing a camera and a wireless transceiver. The wireless transceiver receives wireless packets (e.g., Wi-Fi packets) from one or more mobile devices associated with one or more persons. The channel state information (CSI) is determined based on signals associated with the packets, and first motion characteristics are determined based on the CSI data. Congruently, the camera generates images, and associated image data is received, wherein the image data is associated with the one or more persons. Second motion characteristics are determined based on the image data. The first motion characteristics are matched with the second motion characteristics along with a quantified uncertainty, and the matched motion characteristics are assigned with weights that are based on the second motion characteristics (e.g., image-based). The one or more persons are identified based on the matched motion characteristics and the weights.