40 results about "Visual surveillance" patented technology

Techniques for performing visual surveillance of one or more moving objects are provided. The techniques include registering one or more images captured by one or more cameras, wherein registering the one or more images comprises region-based registration of the one or more images in two or more adjacent frames, performing motion segmentation of the one or more images to detect one or more moving objects and one or more background regions in the one or more images, and tracking the one or more moving objects to facilitate visual surveillance of the one or more moving objects.

A visual surveillance system includes a plurality of surveillance gathering devices, a command and control server operatively connected to each of the plurality of surveillance gathering devices through the Internet, and one or more wireless devices operatively connected to the command and control server through the Internet. The command and control server is programmed to provide wireless control and real-time monitoring of the plurality of surveillance gathering devices at the one or more wireless devices.

An improved solution for detecting events in video is provided, in which a region of interest within a series of video images of the video is monitored. An object at least partially visible within the series of video images is tracked and a fiducial region of the object is identified. The fiducial region is one or more points and/or area(s) of the object, which are relevant in determining whether an alert should be generated. The fiducial region is monitored with respect to the region of interest and a restricted behavior. When the restricted behavior is detected with respect to the region of interest, an alert is generated.

A simplified general model and an associated estimation algorithm is provided for modeling visual data such as a video sequence. Specifically, images or frames in a video sequence are represented as collections of flat moving objects that change their appearance and shape over time, and can occlude each other over time. A statistical generative model is defined for generating such visual data where parameters such as appearance bit maps and noise, shape bit-maps and variability in shape, etc., are known. Further, when unknown, these parameters are estimated from visual data without prior pre-processing by using a maximization algorithm. By parameter estimation and inference in the model, visual data is segmented into components which facilitates sophisticated applications in video or image editing, such as, for example, object removal or insertion, tracking and visual surveillance, video browsing, photo organization, video compositing, etc.

A fast variational on-line learning technique for training a transformed hidden Markov model. A simplified general model and an associated estimation algorithm is provided for modeling visual data such as a video sequence. Specifically, once the model has been initialized, an expectation-maximization (“EM”) algorithm is used to learn the one or more object class models, so that the video sequence has high marginal probability under the model. In the expectation step (the “E-Step”), the model parameters are assumed to be correct, and for an input image, probabilistic inference is used to fill in the values of the unobserved or hidden variables, e.g., the object class and appearance. In one embodiment of the invention, a Viterbi algorithm and a latent image is employed for this purpose. In the maximization step (the “M-Step”), the model parameters are adjusted using the values of the unobserved variables calculated in the previous E-step. Instead of using batch processing typically used in EM processing, the system and method according to the invention employs an on-line algorithm that passes through the data only once and which introduces new classes as the new data is observed is proposed. By parameter estimation and inference in the model, visual data is segmented into components which facilitates sophisticated applications in video or image editing, such as, for example, object removal or insertion, tracking and visual surveillance, video browsing, photo organization, video compositing, and meta data creation.

A security monitoring and enforcement system is provided for monitoring and enforcing control in a secure environment, such as an aircraft. The system includes a security monitoring and enforcement unit (SMEU) having a visual surveillance system and an audio surveillance and communication system. The visual surveillance system is mounted to an enforcement system and housed in a ceiling of an aircraft. The SMEU is remotely operated and monitored by remote control system located on the ground. The security monitoring and enforcement system is operable continuously or when a security breach is detected. The enforcement system is activated and fired to subdue a suspect.

An audio/visual surveillance system for use in mobile vehicles such as patrol cars includes two video cameras producing video signals and four audio sources producing audio signals. The signals are MPEG-2 compressed and streamed in real time with geographic and time data to a digital cartridge-type tape recorder located in the vehicle. A full patrol car shift is recorded on a single tape and, at the end of the shift, the tape is placed in a master sled bay. An MD5 hash authenticates the data for court use. Up to four videos can be synchronized frame-by-frame for simultaneous monitoring. An MPEG-1 stream is sent via wireless to headquarters in real time. One camera captures data external to the vehicle, while the other captures data internal to the vehicle. One audio source captures audio inside the vehicle and another captures dispatcher communications. The other two audio sources are carried by officers.

The invention discloses an infant sleep monitoring system and a method thereof, and relates to the computer vision monitoring field. An infrared laser and a digital CCD camera compose a vision sensing system, and the infrared laser is fixed below the CCD camera through a sensor support; an infant sleep bed is provided with a bedding, line laser projected by the infrared laser is projected on the bedding, the line laser is positioned at the lower part of the body of an infant, and the direction of the line laser is vertical to the direction of the body of the infant; the infrared laser projects onto the bedding to form a laser band, and the laser band is acquired by the digital CCD camera to form an image; the pitching angle of the CCD camera can be adjusted on the sensor support to make the narrow and long laser band appear in the center of the visual field of the CCD camera; and the digital image of the narrow and long band captured by the CCD camera is transmitted to a computer through 1394 image acquisition cards by a transmission cable to complete information processing in order to determine whether the infant kicks the bedding or not, that is, vision measuring software is utilized to detect the laser band and determine whether the infant kicks the bedding or not.

A catamaran airship is tethered to a portable and mobile housing. The roof of the housing will be the landing and take-off place for the airship. Many types of vehicles—truck, ship—can be a mobile base for the housing and its airship. This is primarily a visual surveillance and long-range communication system for day and night, and in all-weather. This system can survey large areas over long periods of time, economically and noiselessly.

The embodiment of the invention provides a sleep state monitoring method and device and a sleep state monitor, and relates to the technical field of computer visual surveillance. The sleep state monitor comprises an infrared sensor and a detection zone control mechanism, a detection zone of the infrared sensor is controlled by the detection zone control mechanism, and the bed surface is detected.The method comprises the steps that whether or not a child sleeps on a bed is judged, and when the child sleeps on the bed, a cyclical scan instruction is sent to the detection zone control mechanism,so that the detection zone control mechanism controls the infrared sensor to conduct partitioning cyclical scanning on the zone, covered with a quilt, of the child; when change of temperature of onezone is obvious, it is judged that the child kicks the quilt, an alarm signal is sent out, and a guardian is reminded of timely treatment.

The invention relates to the field of automobile visual surveillance intelligent safe-guard system, and provides an automobile safety pre-warning method, an automobile safety pre-warning device, equipment and a storage medium. The method comprises the following steps: obtaining monitoring information inside an automobile, wherein the monitoring information comprises environmental state, video dataand using state of the automobile, the video data comprises moving objects inside the automobile, the moving objects comprise persons and/or animals, the using state of the automobile comprises the condition whether an engine operates and whether windows and doors are locked; after the monitoring information is determined to meet abnormal warning conditions, automatically opening the windows anddoors of the automobile, wherein the abnormal warning conditions comprise one of the following items: the oxygen concentration is lower than preset concentration, the temperature is higher than a first temperature value and lower than a second temperature value, the temperature is higher than the second temperature value, the humidity is lower than a first humidity value, the air pressure is higher than a first air pressure value, the air pressure is higher than a second air pressure value, or the concentration of harmful gas is higher than a warning value. By using the scheme, the occurrenceof unnecessary tragedies can be avoided, and the safety defense performance of the automobile is improved.