Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: object detection and tracking

Sortuj według:

Ogranicz wyniki do:

Automatyczne wykrywanie osób w nagraniach uzyskanych przy niedostatecznym oświetleniu

Konieczka A., Chmielewska A., Balcerek J.

Przegląd Elektrotechniczny

2015

R. 91, nr 9

101-104

Artykuł przedstawia system do detekcji osób na nagraniach pochodzących z monitoringu miejskiego na otwartej przestrzeni. Proponowany system został przetestowany w trudnych, nocnych warunkach oświetlenia. W celu polepszenia jakości zarejestrowanych sekwencji wideo zaproponowano algorytm lokalnej poprawy kontrastu. Dzięki niemu detekcja obiektów ruchomych za pomocą GMM (Gaussian mixture model) oraz analizy BLOB (binary large object) jest bardziej precyzyjna. Dodatkowo ruchome obiekty wykryte w obrazie binarnym są śledzone przy użyciu filtru Kalmana, co zwiększa skuteczność algorytmu wykrywającego osoby. W artykule omówiono również dobór parametrów programu oraz sposób akwizycji obrazów.

The article presents the issue related to the intelligent analysis of video sequences, which are obtained from the city monitoring. Analysis of people detection, who passed under the camera in the outdoor scenes, has been tested in low lighting conditions (during the night). In order to improve the quality of acquired video sequences, local contrast enhancement algorithm was used. Thanks to this, detection of moving objects with the use of the GMM (Gausian mixture model) and BLOB (binary large object) analysis is more precise. In addition, detected moving objects in the binary image are tracked with the use of Kalman filter, which increases the efficiency of people detection. Selection of algorithm parameters and video acquisition method were also discussed.

A Novel Approach to Rail Crossing Protection Using Computer Vision and Radio Communications

Rodríguez T.

Machine Graphics and Vision

2011

Vol. 20, No. 1

41-71

In the paper we present an innovative computer vision based rail crossing protection system. A camera installed on top of a mast overlooking the crossing continuously monitors the scene, searching for objects that have stopped on the rail tracks. The system is designed to transmit images of the incident to the approaching trains as soon as any conflictive object has been detected. A simple user interface on board of the train displays the image sequence with a graphical aid clearly identifying the offending object in the image. In that way, train drivers are alerted of the presence of possible obstacles well before the train has approached the crossing. The system we describe operates autonomously for long periods of time without human intervention and adapts automatically to the changing environmental conditions. Several innovations, designed to deal with the above circumstances, are proposed in the paper, including: an adaptive segmentation algorithm, an innovative method for the detection of stopped objects and differentiated approaches for day and night processing.