METHOD FOR PRE-PROCESSING OF LEVEL CROSSING IMAGE

Actuality of problem in the improvement of transport safety at level crossings (LC) is caused by increasing the number of vehicles and reducing discipline of vehicle drivers. One of ways for solution of this problem is associated with using the video surveillance systems for monitoring danger area of level crossing. In such systems due to the limited bandwidth of data channel usually the image compression techniques are used. In this paper the pre-processing method for compression of images is presented. Proposed method accounts unequal subjective informational content of different LC image regions (using fuzzy logic and wavelet transform). Comparison of this method with plain set partitioning in hierarchical trees (SPIHT) technique showed that proposed method allows obtaining better result at image compression in terms of reconstruction quality and compression ratio.