A method is provided. The method includes: obtaining first environmental information and second environmental information, where the first environmental information and the second environmental information are acquired by different sensors; determining, based on the first environmental information, information about a first lane of a first traffic object in the first environmental information, and determining; and determining whether the first traffic object and the second traffic object have an association relationship.

The described aspects and implementations enable fast and accurate verification of radar detection of objects in autonomous vehicle (AV) applications using combined processing of radar data and camera images. In one implementation, disclosed is a method and a system to perform the method that includes obtaining a radar data characterizing intensity of radar reflections from an environment of the AV, identifying, based on the radar data, a candidate object, obtaining a camera image depicting a region where the candidate object is located, and processing the radar data and the camera image using one or more machine-learning models to obtain a classification measure representing a likelihood that the candidate object is a real object.

Systems and methods for construction zone segmentation are provided. The system aligns image level features between a source domain and a target domain based on an adversarial learning process while training a domain discriminator. The target domain includes construction zones scenes having various objects. The system selects, using the domain discriminator, unlabeled samples from the target domain that are far away from existing annotated samples from the target domain. The system selects, based on a prediction score of each of the unlabeled samples, samples with lower prediction scores. The system annotates the samples with the lower prediction scores.

Videos captured in low light conditions can be processed in order to identify an activity being performed in the video. The processing may use both the video and audio streams for identifying the activity in the low light video. The video portion is processed to generate a darkness-aware feature which may be used to modulate the features generated from the audio and video features. The audio features may be used to generate a video attention feature and the video features may be used to generate an audio attention feature. The audio and video attention features may also be used in modulating the audio video features. The modulated audio and video features may be used to predict an activity occurring in the video.

There is provided a computerized system and method of generating a unique identification associated with a gemstone, usable for unique identification of the gemstone. The method comprises: obtaining one or more images of the gemstone, the one or more images captured at one or more viewing angles relative to the gemstone and to a light pattern, thus giving rise to a representative group of images; processing the representative group of images to generate a set of rotation-invariant values informative of rotational cross-correlation relationship characterizing the images in the representative group; and using the generated set of rotation-invariant values to generate a unique identification associated with the gemstone. The unique identification associated with the gemstone can be further compared with an independently generated unique identification associated with the gemstone in question, or with a class-indicative unique identification.

The present application relates to an object prediction method and apparatus, an electronic device, and a storage medium. The method is applied to a neural network and includes: performing feature extraction processing on a to-be-predicted object to obtain feature information of the to-be-predicted object; determining multiple intermediate prediction results for the to-be-predicted object according to the feature information; performing fusion processing on the multiple intermediate prediction results to obtain fusion information; and determining multiple target prediction results for the to-be-predicted object according to the fusion information. According to embodiments of the present application, feature information of a to-be-predicted object may be extracted; multiple intermediate prediction results for the to-be-predicted object are determined according to the feature information; fusion processing is performed on the multiple intermediate prediction results to obtain fusion information; and multiple target prediction results for the to-be-predicted object are determined according to the fusion information. The method facilitates improving the accuracy of multiple target prediction results.

Systems and methods for movement detection are provided. In one example embodiment, a computer-implemented method includes obtaining image data and range data representing a scene external to an autonomous vehicle, the image data including at least a first image and a second image that depict the scene. The method includes identifying a set of corresponding image features from the image data, the set of corresponding image features including a first feature in the first image having a correspondence with a second feature in the second image. The method includes determining a respective distance for each of the first feature and the second feature based at least in part on the range data. The method includes determining a velocity associated with a portion of a scene represented by the set of corresponding image features based at least in part on the respective distance for the first feature and the second feature.

An image forensics system estimates a camera response function (CRF) associated with a digital image, and compares the estimated CRF to a set of rules and compares the estimated CRF to a known CRF. The known CRF is associated with a make and a model of an image sensing device. The system applies a fusion analysis to results obtained from comparing the estimated CRF to a set of rules and from comparing the estimated CRF to the known CRF, and assesses the integrity of the digital image as a function of the fusion analysis.

An urban remote sensing image scene classification method in consideration of spatial relationships is provided and includes following steps of: cutting a remote sensing image into sub-images in an even and non-overlapping manner; performing a visual information coding on each of the sub-images to obtain a feature image Fv; inputting the feature image Fv into a crossing transfer unit to obtain hierarchical spatial characteristics; performing convolution of dimensionality reduction on the hierarchical spatial characteristics to obtain dimensionality-reduced hierarchical spatial characteristics; and performing a softmax model based classification on the dimensionality-reduced hierarchical spatial characteristics to obtain a classification result. The method comprehensively considers the role of two kinds of spatial relationships being regional spatial relationship and long-range spatial relationship in classification, and designs three paths in a crossing transfer unit for relationships fusion, thereby obtaining a better urban remote sensing image scene classification result.

A method includes receiving a first image, receiving a motion dataset, determining a motion level, determining an initialization state, and determining a tracking level. In a first condition, the method includes generating a first image pyramid, detecting a plurality of features in the first image pyramid using a first detector threshold, and generating a first set of detected keypoints from the plurality of features. In a second condition, the method includes generating a second image pyramid, detecting the plurality of features in the second image pyramid using a second detector threshold, the second detector threshold being less restrictive than the first detector threshold, and generating a second set of detected keypoints. In a third condition, the method includes detecting the plurality of features in the first image according to the first detector threshold and generating a third set of detected keypoint.