skip to main content

Attention:

The NSF Public Access Repository (PAR) system and access will be unavailable from 11:00 PM ET on Friday, December 13 until 2:00 AM ET on Saturday, December 14 due to maintenance. We apologize for the inconvenience.


Search for: All records

Award ID contains: 1734206

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. null (Ed.)
    Usage of drones has increased substantially in both recreation and commercial applications and is projected to proliferate in the near future. As this demand rises, the threat they pose to both privacy and safety also increases. Delivering contraband and unauthorized surveillance are new risks that accompany the growth in this technology. Prisons and other commercial settings where venue managers are concerned about public safety need cost-effective detection solutions in light of their increasingly strained budgets. Hence, there arises a need to design a drone detection system that is low cost, easy to maintain, and without the need for expensive real-time human monitoring and supervision. To this end, this paper presents a low-cost drone detection system, which employs a Convolutional Neural Network (CNN) algorithm, making use of acoustic features. The Mel Frequency Cepstral Coefficients (MFCC) derived from audio signatures are fed as features to the CNN, which then predicts the presence of a drone. We compare field test results with an earlier Support Vector Machine (SVM) detection algorithm. Using the CNN yielded a decrease in the false positives and an increase in the correct detection rate.Previous tests showed that the SVM was particularly susceptible to false alarms for lawn equipment and helicopters, which were significantly improved when using the CNN. Also,in order to determine how well such a system compared to human performance and also explore including the end-user in the detection loop, a human performance experiment was conducted.With a sample of 35 participants, the human classification accuracy was 92.47%. These preliminary results clearly indicate that humans are very good at identifying drone’s acoustic signatures from other sounds and can augment the CNN’s performance. 
    more » « less
  2. With the rise in popularity of drones, their use in anti-social activities has also proliferated. Nationwide police increasingly report the appearance of drones in unauthorized settings such as public gatherings and also in the delivery of contraband to prisons. Detection and classification of drones in such environments is very challenging from both visual and acoustic perspective. Visual detection of drones is challenging due to their small size. There may be cases where views are obstructed, lighting conditions are poor, the field of view is narrow, etc. In contrast, acoustic-based detection methods are omnidirectional, however, they are prone to errors due to possible noise in the signal. This paper presents a method of predicting the presence (detection and classification) of a drone using a single microphone and other inexpensive computational devices. A Support Vector Machine classified the spectral and temporal features of pre-segments generated using a sliding window for the audio signal. Additionally, spectral subtraction was used to reconstruct the magnitude spectrum of drone sounds to reduce false alarms. To increase the accuracy of predictions, an added confidence script is proposed based on a queue-and-dump approach to make the system more robust. The proposed system was tested in real time in a realistic environment with various drone models and flight characteristics. Performance is satisfactory in a quiet setting but the system generates excessive false alarms when exposed to lawn equipment. 
    more » « less