Continuous Automatic Bioacoustics Monitoring of Bird Calls with Local Processing on Node Level

In automatic bioacoustic monitoring it is important to do continuous observations to capture rare events, but storage and communication overheads typically prevent continuous real-time monitoring. To overcome this limitation, this paper presents a low complexity local processing method for acoustic signals targeting resource constrained nodes and preprocessing and segmentation techniques in line with the proposed local processing technique for effective and continuous identification of bird calls. This paper also focuses on designing of overall automatic bioacoustic monitoring system including feature extraction and classification. The proposed system with Two-windows method shows maximum accuracy of 93.85% when trained and tested using SVM classifier with 214 real world recordings containing calls of 5 bird species. Having local processing at node level has shown 43% reduction of space requirement at node level and 24% reduction of processing time.