arhet detection ivolves using measurements from sensors to makes a binary decisios as to whether or not a atrget exits at (or near) a particluar point in space. In a typical detection scenario, the opreator deploys a group of sensors around the taracking space. Measurements from the sensors are sent to a central processing center where the detection decision is made. ytpically, each sensor measuremensts will have other relavant data appendend to it, such as a time stamp, the identity of the sensor from wchich it ia Orginated, and the currennt position of the sensor. his paper uses the term “label” to refer to this supplimentary data. In the interest of saving comminication bandwidth between the snesor and the processing center, this work will explore the detection performance when the labeling data is ommitted.
Sensor Network Target Detection with Unlabeled Observarsations
2020-03-01
1569908 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
REPRESENTATION LEARNING FOR OBJECT DETECTION FROM UNLABELED POINT CLOUD SEQUENCES
Europäisches Patentamt | 2024
|MINING UNLABELED IMAGES WITH VISION AND LANGUAGE MODELS FOR IMPROVING OBJECT DETECTION
Europäisches Patentamt | 2023
|