An object detection, tracking and alert system for use in connection with a waste collection vehicle is provided. The system can determine if an external moving object in the surrounding environment of the waste collection vehicle, such as another vehicle or a bicycle, is moving directly towards the waste collection vehicle, and then send one or more alerts to the driver and/or riders on the waste collection vehicle as well as any other waste collection vehicles in the surrounding area.

Systems and methods for improved operations of ski lifts increase skier safety at on-boarding and off-boarding locations by providing an always-on, always-alert system that “watches” these locations, identifies developing problem situations, and initiates mitigation actions. One or more video cameras feed live video to a video processing module. The video processing module feeds resulting sequences of images to an artificial intelligence (AI) engine. The AI engine makes an inference regarding existence of a potential problem situation based on the sequence of images. This inference is fed to an inference processing module, which determines if the inference processing module should send an alert or interact with the lift motor controller to slow or stop the lift.

An apparatus is provided comprising: a determination unit configured to determine a possibility of an abnormality of a subject based on images captured by a surveillance camera with an audio output function; an instruction unit configured to instruct the surveillance camera to produce audio toward the subject in response to the determination of the possibility of an abnormality; an acquisition unit configured to acquire a reaction of the subject to the audio from the surveillance camera; and a detection unit configured to detect whether the subject has an abnormality or not based on the reaction of the subject to the audio.

According to the present disclosure, a method of monitoring a patient on an operating room table is provided. The method comprises receiving image data captured by at least one image capture device; and determining a position of the patient relative to the operating table in dependence on the image data. A corresponding system, computer program and non-transitory memory are also provided.

The invention refers to the field of processing and analyzing video data received from video surveillance cameras, and more specifically, to technologies aimed at detecting a human in a frame and at analyzing their posture for subsequent detection of potentially dangerous situations by video data. The system for detecting potentially dangerous situations contains video cameras, a memory, a graphical user interface (GUI), and a data processing device. Data processing device is configured to receive real-time video data, analyze the received video data, obtain horizontal lines for each of the set corrective vertical lines, split the frame into zones, construct the leg vector based on a pair of the lower limbs key points and determine their belonging to one of the resulting zones, construct a back vector, determine the lower limbs tilt angle between the resulting back vector and the leg vector, determine the human's posture, and detect a potentially dangerous situation, if the human's posture is one of the postures indicating a potentially dangerous situation.

Disclosed herein are apparatuses and methods for detecting a slip, trip or fall event in an environment and sending an alert of the event. An implementation may comprise detecting, in image frames captured by a camera, when an object enters a region of interest, tracking movements of the object, and determining that the object is in a fall-zone. The fall-zone may be specified by a set of line segments, each line segment being defined by points that lie in the region of interest. The implementation may further comprise, when the object is in the fall-zone, recording the position of the object, detecting a slip, trip or fall event when the object transitions from a first position above a predetermined height threshold to a second position below the predetermined height threshold, a pose of the object indicates that the object is lying down, or the object transitions from a vertical to horizontal pose, and sending the alert.

Presented herein are embodiments of a vision-based object perception system for activity analysis, safety monitoring, or both. Embodiments of the perception subsystem detect multi-class objects (e.g., construction machines and humans) in real-time while estimating the poses and actions of the detected objects. Safety monitoring embodiments and object activity analysis embodiments may be based on the perception result. To evaluate the performance of embodiments, a dataset was collected including multi-class of objects in different lighting conditions with human annotations. Experimental results show that the proposed action recognition approach outperforms the state-of-the-art approaches on top-1 accuracy by about 5.18%.

Various embodiments concern video patient monitoring with detection zones. Various embodiments can comprise a camera, a user interface, and a computing system. The computing system can be configured to perform various steps based on reception of a frame from the camera, including: calculate a background luminance of the frame; monitor for a luminance change of a zone as compared to one or more previous frames, the luminance change indicative of patient motion in the zone; and compare the background luminance to an aggregate background luminance, the aggregate background luminance based on the plurality of frames. If the background luminance changed by more than a predetermined amount, then the aggregate background luminance can be set to the background luminance, luminance information of the previous frames can be disregarded, and motion detection can be disregarded.

A machine learning system passively monitors sensor data from the living space of a patient. The sensor data may include audio data. Audio features are generated. A trained machine learning model is used to detect a change in condition. In some implementations, the machine learning model is trained in a learning phase based on training data that includes questionnaires completed by caregivers and identified audio features.

An overdose of opioids can cause the user to stop breathing, resulting in death. A physiological monitoring system monitors respiration based on oxygen saturation readings from a fingertip pulse oximeter in communication with a smart mobile device and sends opioid monitoring information from the smart mobile device to an opioid overdose monitoring service. The opioid overdose monitoring service notifies a first set of contacts when the opioid monitoring information indicates a non-distress stats and notifies a second set of contact when the opioid monitoring information indicates an overdose event. The notification can be a phone call or text message to a specified person, emergency personnel, or first responders, and can include the location of the smart mobile device. The smart mobile device can also include the location of the nearest treatment center having emergency medication used in treating opioid overdose, such as naloxone.