Abstract: A system for detection of a vehicle that blocks an ambulance while the ambulance is responding to an emergency call. The system includes a camera mounted on the ambulance that captures images or video of the surrounding area. A processor, such as an edge computing device with a graphical processing unit (GPU), analyzes the captured data to identify vehicles obstructing the ambulance's path. The system can identify both a leading violating vehicle that directly blocks the ambulance and a primary violating vehicle further ahead that may be causing the obstruction. The system also includes a communication unit to transmit data to a web-based portal or a cloud-based AI engine for further analysis and action.

Abstract: In some embodiments, a method and system for detecting surface changes in a geographical area over time is disclosed. The method includes encoding pre- and post-event images using frozen features of Segment Anything Model (SAM), processing encoded embeddings by a change modeler, processing change embeddings by a change prompter, decoding change embeddings and prompt embeddings using SAM to obtain change masks which include the detected changes.

Abstract: Provided are computer-implemented technologies of identifying visual pollutions. The technologies include training expert models based on an enhanced knowledge distillation paradigm in which a student model learns from a number of teacher models via a customized training approached specifically for achieving efficiency and effectiveness, quality-controlling and fine-tuning the trained expert model in a production environment via continuous training under newly incorporated training data and object classifications and factoring feedbacks of the detection result of the model on new training data and/or new object classifications, deploying and applying the expert model in detecting, tracking, logging, counting, and reporting a set of visual pollution elements in an environment where visual pollutions are to be detected.

Abstract: A tailgating detection system and method includes a single monocular camera, an embedded computer system for determining a tailgating event based on images captured by the camera, the determining of the tailgating event including detecting and tracking wheels of front and tailgating vehicle candidates and determining respective speeds relative to a speed of a vehicle that the camera is mounted and using frame rate of the camera, a location determining device for determining the location where the tailgating event occurred, and a communication unit for transmitting a notification of the tailgating event including the location where the tailgating event occurred.

Abstract: A system, apparatus and method of embedded ego vehicle speed estimation apparatus, including a car-mounted monocular camera for capturing a sequence of video frames of an outdoor scene from a moving car, where the outdoor scene includes a road, as a camera channel, and processing circuitry. The processing circuitry is configured with a single-shot network and a 3D convolutional neural network (3D-CNN), the single-shot network segments features of the road in the video frame sequence and generates a masked-attention map for the segmented road features, a concatenation circuit concatenates the masked-attention map as an additional channel to the camera channel to generate a masked-attention input, and the 3D-CNN network receives the masked-attention input and generates an estimated speed of the ego vehicle based on displacement of the segmented road features in the video sequences.

Abstract: Provided is an edge-device based system and method for real-time detection and dimension estimation of signages by capturing images thereof by using a mounted monocular camera then processing them using a multi-module system that comprises Object Detection, Segmentation, Tracking, and Dimension Estimation modules to detect, segment, track, and estimate dimension of shop boards. The system/method also applies a deep neural network that is trained with labeled data to optimize the model parameters gathered by capturing video from moving vehicle passing through multiple different shops with unconfined locations.

Abstract: An Edge encapsulated method and system for real-time detection of a double parking vehicle blocking parked vehicles by capturing images using a mounted monocular camera then processing using two Semi-Supervised Object Detection (sSOD) stages, that is trained with partly labeled and mostly unlabeled data to optimize the model parameters for the detection problem, gathered by capturing video from moving vehicle passing through multiple different vehicle types and parking systems with unconfined location.