Abstract:
Provided is an apparatus for recognizing an object that includes an object inference module configured to process an original image captured by a camera module and generate an image of a size to be input to a machine learning inference model, wherein the object inference module includes the machine learning inference model, and outputs a result of recognition and classification of an object inferred through the machine learning inference model, and the machine learning inference model processes an input image to infer an object included in the input image.
Abstract:
A dynamic packet relay method of a personal area network (PAN) coordinator in a sensor network includes receiving a Child_Register message that includes information about a device associated with a coordinator and building or updating a network hierarchical structure; monitoring reception of a packet or a beacon from the coordinator and determining whether the coordinator is defective or not; and in response to a determination that the coordinator is defective, changing the current coordinator to one of devices belonging to a PAN as a new coordinator.
Abstract:
An intruder location-based dynamic virtual fence configuration and a multiple image sensor device operation method are provided. A method of detecting an intruder based on a virtual fence includes detecting an intruder invading a virtual fence set in a protection area by using a first image sensor device, and tracking the intruder through cooperation with second image sensor devices adjacent to the first image sensor device, based on information of the intruder.
Abstract:
Provided are a method and system for detecting a UAV using a plurality of image sensors. A method of detecting a UAV includes detecting, by each of a plurality of detection image sensors, a UAV in a UAV detection area, transmitting, when the UAV is detected, position information of the detection image sensor detecting the UAV and distance information of the UAV to a classification image sensor, acquiring, by the classification image sensor, a magnified image of the UAV by setting a parameter of a camera of the classification image sensor according to the position information and the distance information, and classifying a type of the UAV by analyzing the magnified image.
Abstract:
An apparatus for dynamically configuring a wireless sensor relay network for monitoring train activity according to the present invention includes a plurality of wireless sensors that wirelessly transmit sensor data obtained by measuring heat and vibration of a train running unit, a plurality of coordinator units that are located in train cars, and receive the sensor data from one or more wireless sensors located within the same train car, a plurality of wireless relay units that are located in the train cars, form a wireless sensor relay network with the wireless relay unit located in a neighboring train car, and transmit the sensor data received from the coordinator units, and a gateway unit that receives the sensor data from the plurality of wireless relay units through the wireless sensor relay network, and transmits the received sensor data to a control center.
Abstract:
Disclosed is a wireless location determination apparatus using weighted values in a wireless communication network, including: a fixed infrastructure searching unit configured to search and accept information of nodes to be located and neighbor fixed infrastructures; an infrastructure combination generating unit configured to generate fixed infrastructure combinations to be used for location determination from the information of the fixed infrastructures; a location determination information element extracting unit configured to extract location determination information elements between the fixed infrastructures from each generated fixed infrastructure combination; a weighted value calculating unit configured to allocate the weighted values to each fixed infrastructure combination using the extracted location determination information elements; a fixed infrastructure combination selecting unit configured to select the fixed infrastructure combinations for location determination using the allocated weighted values; and a location calculating unit configured to calculate locations of the nodes to be located using the selected fixed infrastructure combinations.
Abstract:
An exemplary embodiment provides an intruder detection method capable of accurately detecting an intruder and estimating an abnormal behavior of the intruder even when viewpoints of acquired images are different from each other. An intruder detection method is suitable for being performed by an intruder detection device for detecting an intruder based on images and includes: receiving input images acquired by multiple cameras; extracting feature maps associated with a plurality of viewpoints by applying the input images to a plurality of convolutional neural networks provided separately for the plurality of viewpoints of the images; and detecting the intruder based on the feature maps associated with the plurality of viewpoints.
Abstract:
A reconnaissance UAV and a surveillance flight method of the reconnaissance UAV which can reduce a number of required reconnaissance UAVs are provided. The surveillance flight method for detecting an unauthorized UAV includes: defining multiple flight passages in a UAV no-fly zone for a plurality of reconnaissance UAVs; controlling each of the plurality of reconnaissance UAVs to fly across adjacent flight passages at an interval by crossing a border of the adjacent flight passages; and controlling at least one of an image sensor and a noise sensor mounted on the reconnaissance UAV to dynamically change a direction detection thereof.
Abstract:
A method of transmitting control information by an end node in a wireless communication system supporting multi-channel transmission includes: transmitting control information to a center node on a first channel among multiple channels within a control period of a wireless frame when the first channel is in an idle state; transmitting the control information to the center node on a second channel when the first channel is not in the idle state and the second channel is in the idle state, the second channel being selected from channels other than the first channel among the multiple channels; and transmitting the control information to the center node in a subsequent wireless frame when the second channel is not in the idle state.
Abstract:
A method for providing a traffic safety service of a traffic safety service server communicating with a client terminal includes: receiving sensor data of each sensor from the client terminal; classifying the sensor data into data according to at least one specific time slot for each sensor and calculating a safety score of each of the at least time slot; calculating an average of the safety scores of the at least time slot and calculating a safety score for each sensor, and calculating a safety index on the basis of the safety score for each sensor and a weight assigned to each sensor.