186 results about "Object detector" patented technology

The invention belongs to the technical field of ship collision avoidance, discloses a ship collision avoidance early warning method and system based on vision and AIS data collaborative perception, and firstly provides an enhanced YOLO (E-YOLO) target detector which can detect a ship in a complex environment in a high-precision and real-time manner and perform ship tracking and visual trajectory extraction in combination with a DeepSORT algorithm. Secondly, a homography coordinate conversion method based on multiple frames of static images is provided, conversion between a pixel coordinate system and a world coordinate system can be realized without accurate camera calibration, and the fusion precision of visual data and AIS data is improved. AIS and visual information are matched through a K-D tree algorithm, AIS data are projected to visual coordinates, and accurate matching of heterogeneous data is achieved. The system is provided with ship illegal behavior judgment and collision early warning rules, behaviors such as overspeed and abnormal AIS closing can be recognized, and early warning is triggered. Experiments prove that the method provided by the invention is strong in adaptability and high in robustness, and can effectively improve the ship monitoring and traffic management level of the bridge water area.

Techniques for determining a presence of an object, especially an object such as animal or debris, in a path of a vehicle, are discussed herein. For example, sensors of various modalities, which may include multispectral sensors, may capture data representing an environment the vehicle is traversing. In examples, one or more trained machine learned (ML) models, operating on a vehicle computing system, may detect and / or classify objects in the environment, based on input data of one or more modalities or spectral bands. The ML models may be pre-trained using training data including real sensor data, synthetic data, and / or augmented data, along with auto-generated annotations. In some examples, hyperspectral data may be used to identify materials associated with detected objects. A confidence score associated with the detection of the object may also be computed. The vehicle may be controlled based on detection of the object and its classification.

Techniques are discussed herein for generating three-dimensional (3D) representations of an environment based on two-dimensional (2D) image data, and using the 3D representations to perform 3D object detection and other 3D analyses of the environment. 2D image data may be received, along with depth estimation data associated with the 2D image data. Using the 2D image data and associated depth data, an image-based object detector may generate 3D representations, including point clouds and / or 3D pixel grids, for the 2D image or particular regions of interest. In some examples, a 3D point cloud may be generated by projecting pixels from the 2D image into 3D space followed by a trained 3D convolutional neural network (CNN) performing object detection. Additionally or alternatively, a top-down view of a 3D pixel grid representation may be used to perform object detection using 2D convolutions.

A computer-implemented method for training a machine learning, ML, model to perform object detection, the method comprising: obtaining a first training dataset comprising a plurality of unlabelled images, each unlabelled image containing at least one object; analysing the first training dataset by using an object detector module of the ML model; forming a second training dataset using the unlabelled images of the first training dataset and their corresponding extracted bounding boxes and pseudo-labels; and training the object detector module, using the second training dataset, to output bounding boxes and pseudo-labels for input pseudo-labelled images.

The invention belongs to the field of computer vision and artificial intelligence security, and discloses a self-adaptive frequency domain adversarial training method and device for a target detector, the target detector comprises a repair module and a pedestrian detector which are connected in series, and the input of the repair module is connected with the output of a patch detector; the self-adaptive frequency domain adversarial training method comprises the following steps: losses in joint training comprise standard target detection losses, repair consistency losses on a frequency domain based on a frequency domain image corresponding to a training image and a clean image, and repair dependence losses based on a detected average precision mean value; according to the invention, the end-to-end joint training is carried out through the restoration module and the subsequent pedestrian detector, and the optimization target of the restoration module is directly aligned with the improvement of the detection robustness, so that the confrontation disturbance is eliminated as far as possible, and meanwhile, the key semantic information of the detection task is reserved to the maximum extent. The separation of the performance of the repair module and the pedestrian detector is avoided, and the detection robustness is improved.

Systems and methods for a multi-camera object detector having two or more backbone models. In particular, systems and methods are provided for including two or more backbone machine learning models, with one backbone optimized for speed and the other backbone optimized for precision. In particular, the first backbone can be highly accurate but slower than the second backbone and with a higher computer resource usage. The second backbone can be fast and efficient but have lower accuracy for object detection. In some examples, the second backbone can use fewer images and / or lower resolution images. The determination of which backbone to use can be based on fixed rules, or it can be determined based on another machine learning component. The outputs from the first and second backbones for each camera can be combined together into a unified representation, such as a bird's eye view (BEV) space.

Systems, methods, and storage media for manifesting a virtual object in a virtual environment are disclosed. Exemplary embodiments may: receive, at a first physical object detector, a first signal, from a first physical object-associated element in a first physical environment; identify, at a first value identification module, based on the first signal, a first value associated with the first signal; identify, at a first virtual object identification module, based on the first value, a first virtual object; and manifest, at a first virtual environment output device, a first manifestation of the first virtual object in a first manifestation of the first virtual environment.

A method for generating training data for an object detector. The method includes receiving a plurality of optical images of a scene, each camera showing the scene from a respective viewing direction of a plurality of different viewing directions, receiving a plurality of sensor data elements, each sensor data element including sensor data other than optical image data of the scene from a respective sensing direction of a plurality of different sensing directions, training a first neural radiance field using the plurality of optical images to generate, for each 3D point of the scene, a respective value of a predetermined feature, training a second neural radiance field using the plurality of sensor data elements to generate, for each 3D point of the scene, a respective sensor data value and generating training data elements for the object detector using the first and the second neural radiance field.

Unlike existing methods, using LIDAR and 2D-cameras for detection and limit in providing robust tracking of objects, the method disclosed addresses the technical challenge by utilizing 3D-LIDAR points clouds, 2D-camera images and additionally 2D-BEV from 3D LIDAR point clouds to provide, robust, seamless, 360 tracking of objects. The method independently detects, and tracks objects captured by each of the LIDAR, 2D-camera set up mounted on an autonomous vehicle. Detection and tracking is performed on 2D-Camera and 2D-BEV and fused with 3D-Lidar tracker, Additionally, non-occluded area of an object in 2D-bounding boxes, is identified by superimposing panoptic segmentation output with 2D-BB, that helps to eliminate the lidar points falling on the irrelevant objects and provides accurate real world position of the detected objects in the point cloud. An enhanced 2D object detector based on a customized NN architecture employing MISH activation function is also introduced.

Example solutions for ranking object detection results generate or receive a plurality of segmentation masks each corresponding to one or more images. Each segmentation mask of each plurality of segmentation masks is generated using a different object detector or setting options. A quality predictor assigns a quality score to each segmentation mask, without using ground truth for the image(s). A set (one or more, but less than all) of the highest quality scores is identified for each image. In some examples, an image processing task is performed using the segmentation masks having an assigned quality score that is within the set of highest quality scores. In some examples, only the segmentation mask having the highest quality score for an image is used in the image processing task. In some examples, a quality threshold is provided, and the segmentation masks meeting the quality threshold are used in the image processing task.

A method and server for training an Object Detector (OD) to detect objects in 3D point clouds are provided. The method comprises: during a first stage of a training pipeline: training the OD using a source domain dataset to detect the objects in a source domain, thereby generating a first trained OD; during a second stage of the training pipeline: training the first trained OD using a target domain dataset to detect the objects in a target domain, thereby generating a second trained OD; and during a third stage of the training pipeline: generating, based on the source domain dataset and the target domain dataset, a cross-domain dataset; and training the second trained OD using the cross-domain dataset to detect objects in both the source domain and the target domain, thereby generating a cross-domain OD.

The invention discloses a pedestrian re-identification method based on image feature fusion and coding, and the method comprises the steps: constructing a target detector based on a cavity convolution feature pyramid network according to a constructed mixed receptive field module and a low-layer embedded feature pyramid module; classifying and positioning the to-be-detected target images with different scales to obtain divided pedestrian images; a dense feature pyramid network DFPN constructed by a feature extraction module RVNet, a feature enhancement module I DPFM, a feature enhancement module II IRFB and a feature aggregation module Heads is adopted to extract features in a pedestrian image and enhance the features; a pedestrian feature learning method module based on multi-view comparison predictive coding is constructed and embedded into a dense feature pyramid network (DFPN), and multi-view feature reconstruction is performed on input image features by using kernel density estimation and is combined with comparison learning, so that the model learns pedestrian feature expressions of different views. The inter-class difference is increased, and the intra-class similarity is kept; and pedestrian re-identification in the image is realized.

An auto-exposure control is proposed for high dynamic range images, along with a neural network for exposure selection that is trained jointly, end-to-end with an object detector and an image signal processing (ISP) pipeline. Corresponding method and system for high dynamic range object detection are also provided.

An auto-exposure control is proposed for high dynamic range images, along with a neural network for exposure selection that is trained jointly, end-to-end with an object detector and an image signal processing (ISP) pipeline. Corresponding method and system for high dynamic range object detection are also provided.

An auto-exposure control is proposed for high dynamic range images, along with a neural network for exposure selection that is trained jointly, end-to-end with an object detector and an image signal processing (ISP) pipeline. Corresponding method and system for high dynamic range object detection are also provided.

The invention belongs to the field of underwater operation, and particularly discloses a binocular vision servo method for autonomous operation of an underwater vehicle-double-arm manipulator, and the method comprises the steps: obtaining a two-dimensional image and a depth image in front of the underwater vehicle-double-arm manipulator; inputting the two-dimensional image into a lightweight target detector to obtain a target recognition frame; designing a target three-dimensional coordinate observation value acquisition method based on the shape of an identification frame so as to reduce the influence of a parallax hole; solving an equipment motion matrix based on the three-dimensional coordinates of the key points in the images at the adjacent moments; a nonlinear Kalman filtering method based on a motion matrix is designed by taking the three-dimensional coordinates of the target as state vectors, and continuous estimation of the target position is realized; a target three-dimensional coordinate is used as a reference, an aircraft-manipulator is driven to move, and a two-dimensional image is used for driving a tail end joint of the manipulator to rotate, so that an actuator of the manipulator can effectively clamp the target after the manipulator reaches the target. According to the invention, the autonomy and intelligence of underwater operation can be effectively improved.

3D objection detection is a computer vision task that generally refers to detecting (e.g. classifying and localizing) an object in 3D space from an image or video that captures the object. This computer vision task has many useful applications, such as autonomous driving applications which rely on the detection of 3D objects in a local environment to make autonomous driving decisions. State-of-the-art 3D object detectors generally rely on machine learning, but current training processes for these detectors do not specifically address false negative detections, or missed objects, which are often caused by occlusions and / or cluttered backgrounds in the given image / video. Reducing false negatives is crucial for many downstream applications, particularly autonomous driving applications which rely on accurate detection of obstacles for making safe driving decisions. The present disclosure provides for a multi-stage training process that reduces false negative detections by 3D object detectors.

A vehicle blind-spot reduction device includes side-view mirrors on sides of a vehicle, an actuator configured to move an optical display of each of the side-view mirrors, a detector configured to detect a display position of the optical display, a surrounding environment information acquirer configured to acquire environment information on surrounding of the vehicle, a moving object detector configured to detect a moving object running beside the vehicle on the basis of the surrounding environment information, a blind spot setter configured to set a blind spot of each of the side-view mirrors on the basis of the display position of the optical display, and a display surface adjuster. Based on determining that the moving object has entered the blind spot, the display surface adjuster causes the actuator to operate to adjust the display position of the optical display.

Systems and methods for site-based calibration of object detection rules, such as for surveillance video cameras, are described. Video data from a video image sensor may be processed using an object detector to determine object data for a detected object. The object data may be post-processed using a post-processing rule set to determine whether the detected object violates the post-processing rule set. Event notifications to a video surveillance application may be prevented responsive to the object data violating the post-processing rule set.

An auto-exposure control is proposed for high dynamic range images, along with a neural network for exposure selection that is trained jointly, end-to-end with an object detector and an image signal processing (ISP) pipeline. Corresponding method and system for high dynamic range object detection are also provided.

An image capturing apparatus includes an image capturing unit, a driving unit configured to drive the image capturing unit, and at least one processor. The at least one processor is configured to function as a motion vector detector configured to detect motion vectors based on image data output from the image capturing unit, an object detector configured to detect a plurality of moving objects based on the motion vectors, and a controlling unit configured to perform tracking control by controlling the driving unit. The controlling unit calculates respective evaluation values of the plurality of moving objects based on at least one of (a) information on the plurality of moving objects, (b) information on a shake of the image capturing apparatus, and (c) information on a driving state of the driving unit. The controlling unit controls the driving unit based on the evaluation values.

The present invention discloses a target detection method in a bad weather scenario based on degradation consistency, which relates to the technical field of image processing. A synthetic dataset is used as a fully annotated dataset, supplemented with a small number of bad weather images in real scenarios, and the synthetic dataset is converted into an image dataset in a bad weather scenario through a GCN network; the BDN and LCN networks are jointly trained, and the images in the real bad weather scenario and the simulated synthetic images are respectively input into the networks to train the networks. Among them, the GCN network uses an image-image style conversion algorithm to convert a large number of synthetic datasets into images in a bad weather scenario, effectively alleviating the problem of insufficient image annotation in a bad weather scenario. The BDN network uses an anchor-free object detector as the basic detector to avoid the problem of target loss caused by the region screening mechanism in the bad weather scenario images. The LCN is used to fine-tune the features generated by the synthetic images, and the details are closer to the low-quality images in the original bad weather scenario.

Provided is a training method for updating a deep learning-based object detector of an autonomous vehicle to adapt to a driving environment, the method comprising (a)(i) inputting a training image corresponding to the driving environment into an environment-specific object detector to cause the kth environment-specific object detector to (i-1) generate an environment-specific feature map through convolution, (i-2) generate an environment-specific pooling feature map through ROI pooling, and (i-3) generate environment-specific object detection information by applying a full connection operation to the kth environment-specific pooling feature map, (ii) inputting the environment-specific feature map into an environment-specific ranking network, (ii-1) generating an environment-specific segmentation map through an environment-specific deconvolution layer, and (ii-2) generating an environment-specific ranking score through an environment-specific discriminator, and (b) training the environment-specific object detector, training the environment-specific deconvolution layer, and training the environment-specific discriminator.

A headlamp device includes a headlamp, an object detector, and a controller. The headlamp is mounted on a vehicle and includes a light emitting unit composed of multiple light emitting cells. The object detector detects an object around the vehicle and generates an object detection signal including object coordinates corresponding to a location of the detected object. The controller controls light of the headlamp based on information on the object coordinates. The controller may control the light emitting unit such that at least some light emitting cells are turned off according to an object detection signal. Each of multiple light emitting units includes a circuit board, the multiple light emitting cells separated from each other on the circuit board, a molding member formed between the light emitting structures, and a protective member formed on the molding member to surround sides of the multiple wavelength conversion members while filling a gap between the multiple wavelength conversion members.

A driving assistance device includes: a vehicle surrounding image aquisitor acquiring a captured image of surroundings of a vehicle or by processing the captured image, as a vehicle surrounding image where the surroundings of the vehicle are visually recognized from a set viewpoint; an object detector detecting an object of attention being an object present around the vehicle requiring attention; a model image acquisitor acquiring a model image indicating an appearance of the object of attention; an assistance image generator generating an assistance image where the model image is synthesized with the vehicle surrounding image according to a position of the object of attention; and an image display displaying the assistance image on a display device such that the vehicle surrounding image excluding the model image has a luminance difference or a contrast ratio with the model image increasing stepwise as a distance from the viewpoint increases.

A power transmitter (101) provides wireless power to a power receiver (105). The power transmitter (101) comprises a transmitter coil (103) generating a power transfer signal. A communicator (307) is arranged to communicate using a communication carrier and an object detector (is arranged to detect objects. An update circuit (315) receives (701) a power receiver identity modulated on communication carrier by a power receiver in response a detection of the power receiver. The identity is stored and transmitted to an update device by modulation of the communication carrier when the update device is detected. Update data modulated on the communication carrier by the update device is received and stored with a link to the identity. When a power receiver is subsequently detected, a new identity is received (711) and update data linked to this identity is retrieved (713). The retrieved update data is then transmitted to the power receiver which may then perform an update using the update data.

A method and system perform incremental learning object detection in images and / or videos without catastrophic forgetting of previously learned object classes. A two-stage neural network object detector is trained to locate and identify objects belonging to additional object classes by iteratively updating the two-stage neural network object detector until an overall detection accuracy criterion is met. The update is performed to balance minimizing the loss of the initial ability to locate and identify objects belonging to previously learned object classes and maximizing the ability to additionally locate and identify objects belonging to additional object classes. Evaluating whether the overall detection accuracy criterion is met compares the output of an initial version of the two-stage neural network object detector with current region proposals output by a current version of the two-stage neural network object detector to determine a region proposal distillation loss and a previously learned object recognition distillation loss.

Systems and techniques are described for suppressing false positive notifications for detected objects. In various examples, first bounding box data indicating a detection of a first class of object in a first frame of image data may be received from an object detector. Second bounding box data indicating a prior detection of the first class of object in a second frame of image data may be determined. A first value representing a similarity between the first bounding box data and the second bounding box data may be determined. A notification associated with the detection of the first class of object in the first frame of image data may be suppressed based at least in part on the first value.

The present application relates to a kind of method and system for detecting general object based on dynamic inference network.The method comprises: based on the given general object detector, construct the dynamic inference object detector of multiple outlet;For the dynamic inference object detector of multiple outlet, insert multi-scale adaptive gating network;Using the training strategy of no hyperparameter, train the dynamic inference object detector of multiple outlet and the multi-scale adaptive gating network;Using the dynamic inference object detector of multiple outlet and the multi-scale adaptive gating network of training completion, using variable time delay inference strategy carries out general object detection.The present application can be widely applied in the deployment of a variety of general object detector, and then be applied to intelligent security, automatic driving, unmanned aerial vehicle survey and a variety of application scenarios, to realize the effective deployment of the same model in a variety of hardware requirements, application, reduce the consumption of manpower, material resources and financial resources.