No abstract

No abstract

The main purpose of this work is to propose a robust approach for dangerous sound events detection (e.g. gunshots) to improve recent surveillance systems. Despite the fact that the detection and classification of different sound events has a long history in signal processing, the analysis of environmental sounds is still challenging. The most recent works aim to prefer the time-frequency 2-D representation of sound as input to feed convolutional neural networks. This paper includes an analysis of known architectures as well as a newly proposed Independent Channel Residual Convolutional Network architecture based on standard residual blocks. Our approach consists of processing three different types of features in the individual channels. The UrbanSound8k and the Free Firearm Sound Library audio datasets are used for training and testing data generation, achieving a 98 % F1 score. The model was also evaluated in the wild using manually annotated movie audio track, achieving a 44 % F1 score, which is not too high but still better than other state-of-the-art techniques.

Time of Flight (ToF) sensors are the source of various errors, including the multi-camera interference artifact caused by the parallel scanning mode of the sensors. This paper presents the novel Importance Map Based Median filtration algorithm for interference artifacts suppression, as the potential 3D filtration method. The approach is based on the processing of multiple depth frames, using the extraction of the interference region and application of the interpolation. Considering the limitations and good functionalities of proposed algorithm, the combination with some standard methods was suggested. Performance of the algorithm was evaluated on the dataset consisting of the real-world objects with different texture and morphology against popular filtering methods based on neural networks and statistics.

No abstract