Flexible hardware designs for camera calibration and image pre-processing are disclosed for vehicles including autonomous driving (AD) vehicles. For one example, a sensor unit includes a sensor interface, host interface, and pre-processing hardware. The sensor interface is coupled to a plurality of cameras configured to capture images around an autonomous driving vehicle (ADV). The host interface is coupled to a perception and planning system. The pre-processing hardware is coupled to the sensor interface to receive images from the plurality of cameras and to perform one or more pre-processing functions on the images and to transmit pre-processed images to the perception and planning system via the host interface. The perception and planning system is configured to perceive a driving environment surrounding the ADV based on the pre-processed images and to plan a path to control the ADV to navigate through the driving environment. The pre-processing functions can adjust for different calibrations and formats across the plurality of cameras.

A method, system and computer program product are configured to analyze an image of a vehicle to determine a characteristic of the vehicle, such as may be represented by or otherwise at least partially defined by the shadow cast by the vehicle. In the context of a method, information is received identifying a vehicle from a raster image and the pixel values of the raster image are evaluated to identify pixels having pixel values representative of a shadow associated with the vehicle. The method also modifies a representation of the shadow by modifying the pixel values of the pixels based upon a shape of the vehicle such that the representation of the shadow, as modified, has a shape corresponding to the shape of the vehicle. The method additionally determines a characteristic of the vehicle based upon the representation of the shadow, as modified, that is associated with the vehicle.

Presented are systems and methods for 3D reconstruction from videos using an unsupervised learning framework for depth and normal estimation via edge-aware depth-normal consistency. In embodiments, this is accomplished by using a surface normal representation. Depths may be reconstructed in a single image by watching unlabeled videos. Depth-normal regularization constrains estimated depths to be compatible with predicted normals, thereby, yielding geometry-consistency and improving evaluation performance and training speed. In embodiments, a consistency term is solved by constructing depth-to-normal layer and normal-to-depth layers within a deep convolutional network (DCN). In embodiments, the depth-to-normal layer uses estimated depths to compute normal directions based on neighboring pixels. Given the estimated normals, the normal-to-depth layer may then output a regularized depth map. Both layers may be computed with awareness of edges within the image. Finally, to train the network, the photometric error and gradient smoothness for both depth and normal predictions may be applied.

A method of performing context-based autonomous perception is provided. The method includes acquiring perception sensor data as an image by an autonomous perception system that includes a processing system coupled to a perception sensor system. Feature extraction is performed on the image by the autonomous perception system. The feature extraction identifies one or more features in the image. Contextual information associated with one or more conditions present upon acquiring the perception sensor data is determined. One or more labeled reference images are retrieved from at least one of a contextually-indexed database based on the contextual information, a feature-indexed database based on at least one of the features extracted, and a combined contextually- and feature-indexed database. The image is parsed, and one or more semantic labels are transferred from the one or more labeled reference images to form a semantically labeled version of the image.

The invention relates to a device for the biometric acquisition and processing of an image of a part of the human body with dermatoglyphs, comprising a contact surface (3) configured so that the part of the human body is affixed to this contact surface (3), a light source (4) configured to project onto the part of the human body a light pattern having a sinusoidal modulation of light intensity in a main direction with a target frequency, an imager (2) configured to acquire an image, and an automated data processing system (7) configured to implement a fraud detection method and a biometric identity recognition method using a periodic component parameter representative of an amplitude of a sinusoidal oscillation of light intensity in the acquired image in accordance with the main direction at the target frequency.

A facial expression recognition training system includes a training module, feature database, a capturing module, a recognition module and an adjusting module. The training module trains a facial expression feature capturing model according to known face images. The feature database stores known facial expression features of the known face images. The capturing module continuously captures first face images, and the facial expression feature capturing model outputs facial expression features of the first face images according to the first face images. The recognition module compares the facial expression features and the known facial expression features, and fit the facial expression features to the first known facial expression features that is one kind of the known facial expression feature accordingly. The adjusting module adjusts the facial expression feature capturing model to reduce the differences between the facial expression features and the known facial expression features.

This invention provides an image searching method based on feature extraction to determine at least one sample image similar to the image to be searched, including the following steps: a. feature extraction on all sample images to obtain all corresponding feature information, while all sample images are I.sub.1, I.sub.2, . . . , I.sub.S and all said feature information corresponding to all sample images are V.sub.1, V.sub.2, . . . , V.sub.S; b. creating an index tree based on all of said feature information; c. obtaining the feature information corresponding to the image to be searched based on the feature extraction; d. determining said feature information corresponding to at least one sample image having a minimum distance from the image to be searched based on the index tree and the feature information of the image to be searched. The invention has powerful functions and simple operation, and is able to avoid interference of background, text annotation and image merging during processing and filtering of feature extraction, which has good search results and high commercial value.

The present invention relates to an autonomous moving device, including a camera and a camera heating device, where the camera heating device includes a heating module, and the heating module is configured to heat a lens of the camera to remove water mist on the lens. The present invention can effectively avoid a freezing or water mist phenomenon of a camera, thereby improving the photographing performance.

Disclosed is a quotation method executed by a computer, comprising: obtaining structure parameters and electrical parameters of a product (S101); constructing an external view of the product by using the structure parameters of the product, and performing similarity comparison on the external view of the product and the external view of a historical product to obtain an appearance similarity sorting (102); performing similarity comparison on the electrical parameters of the product and the electrical parameters of the historical product to obtain an electrical parameter similarity sorting (103); on the basis of the cost weights of a structural member and an electrical component and the appearance similarity sorting and the electrical parameter similarity sorting, obtaining a comprehensive sorting which is based on the structure parameters and the electrical parameters (S104); and determining, based on the comprehensive sorting, a bill of materials of the product, and calculating, based on the bill of the materials of the product, the product quotation (105).

A method for pattern recognition may be provided, comprising: receiving data; processing the data with a trained convolutional neural network so as to recognize a pattern in the data, wherein the convolutional neural network comprises at least: an input layer, at least one convolutional layer, at least one batch normalization layer, at least one activation function layer, and an output layer; and wherein processing the data with a trained convolutional neural network so as to recognize a pattern in the data comprises: processing values outputted by a batch normalization layer so that the histogram of the processed values is flatter than the histogram of the values, and outputting the processed values to an activation function layer. A corresponding apparatus and system for pattern recognition, as well as a computer readable medium, a method for implementing a convolutional neural network and a convolutional neural network are also provided.