National Repository of Grey Literature 3 records found  Search took 0.01 seconds. 
Configurable Embedded Photo/Video Trap with Storing Data and Self Adaptation to Surroundings
Výborný, Filip ; Šimek, Václav (referee) ; Strnadel, Josef (advisor)
This diploma thesis deals with a design and construction of an embeded camera trap with a video recording and night vision support, which is able to self adapt to surroundings. The device is based on the Raspberry Pi platform and configurable by touch screen control with a user-friendly graphical interface. Also the web-application for easy remote administration was developed in Ruby On Rails framework. The camera trap was built and successfully tested under the real conditions. There are also typical application cases and requirements for camera trap construction described in this thesis.
Identifikace železničních vozů na základě obrazové informace
ŠEPS, Pavel
This master's thesis focuses on the design and implementation of railway wagon indetification system based on the identifying information on the side of each wagon. It describes the search for the optimal image preprocessing, comparison of OCR services, search for the suitable technologies and evaluation of the quality of the finished application. Part of this thesis also describes existing solutions and the application development and functionality. To obtain the images of the wagons, a photo trap is designed and assembled, which is then located near the train track. A custom neural network was built to find the identifying information and a custom annotation application was developed to create the test and training sets. The final identification application then implements this neural network. It also uses Azure OCR services. It is designed to automate the manual process and is ready for use in real operation.
Configurable Embedded Photo/Video Trap with Storing Data and Self Adaptation to Surroundings
Výborný, Filip ; Šimek, Václav (referee) ; Strnadel, Josef (advisor)
This diploma thesis deals with a design and construction of an embeded camera trap with a video recording and night vision support, which is able to self adapt to surroundings. The device is based on the Raspberry Pi platform and configurable by touch screen control with a user-friendly graphical interface. Also the web-application for easy remote administration was developed in Ruby On Rails framework. The camera trap was built and successfully tested under the real conditions. There are also typical application cases and requirements for camera trap construction described in this thesis.

Interested in being notified about new results for this query?
Subscribe to the RSS feed.