Abstract
Most sound imaging instruments are currently used as measurement tools which can provide quantitative data, however, a uniform method to directly and comprehensively evaluate the results of combining acoustic and optical images is not available. Therefore, in this study, we define a localization error index for sound imaging instruments, and propose an acoustic phase cloud map evaluation method based on an improved YOLOv4 algorithm to directly and objectively evaluate the sound source localization results of a sound imaging instrument. The evaluation method begins with the image augmentation of acoustic phase cloud maps obtained from the different tests of a sound imaging instrument to produce the dataset required for training the convolutional network. Subsequently, we combine DenseNet with existing clustering algorithms to improve the YOLOv4 algorithm to train the neural network for easier feature extraction. The trained neural network is then used to localize the target sound source and its pseudo-color map in the acoustic phase cloud map to obtain a pixel-level localization error. Finally, a standard chessboard grid is used to obtain the proportional relationship between the size of the acoustic phase cloud map and the actual physical space distance; then, the true lateral and longitudinal positioning error of sound imaging instrument can be obtained. Experimental results show that the mean average precision of the improved YOLOv4 algorithm in acoustic phase cloud map detection is 96.3%, the F1-score is 95.2%, and detection speed is up to 34.6 fps. The improved algorithm can rapidly and accurately determine the positioning error of sound imaging instrument, which can be used to analyze and evaluate the positioning performance of sound imaging instrument.
Highlights
Sound imaging instruments, known as acoustic cameras, are a special kind of acoustic analysis equipment that use a microphone array to measure the distribution of the sound field in a certain spatial range
VideoItimages taken bythe theacoustic camera phase installed ongenerated the arrayusing in a transparent way visualize measurement superimposes map the microphone to form a so-called acoustic phase cloud map, from which the noise state of the measured object can array with video images taken by the camera installed on the array in a transparent way to form be visually analyzed
The localization error of sound imaging instrument tends to decrease with an increase in the frequency of the target sound source, and the longitudinal localization error is more obviously affected by frequency
Summary
Known as acoustic cameras, are a special kind of acoustic analysis equipment that use a microphone array to measure the distribution of the sound field in a certain spatial range. Is a sound imaging instrument’s calibration scheme needed, and a suitable method should be developed to assess source localization results in cloud maps. The image processing method extracts the detection object on the acoustic phase cloud map and compares it with the actual target position to obtain its localization error. YOLOv4 algorithm, which combines the advantages of the high precision of deep learning and meeting real-time applications and divides sound source localization results into lateral and longitudinal localization errors. This method trains the neural network by using acoustic phase cloud maps generated by sound imaging instruments to locate sound sources at different positions as a dataset. After converting them into physical space coordinates through calibration, lateral and longitudinal positioning errors are calculated
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
