EmbeddedPigDet—Fast and Accurate Pig Detection for Embedded Board Implementations

Abstract

Automated pig monitoring is an important issue in the surveillance environment of a pig farm. For a large-scale pig farm in particular, practical issues such as monitoring cost should be considered but such consideration based on low-cost embedded boards has not yet been reported. Since low-cost embedded boards have more limited computing power than typical PCs and have tradeoffs between execution speed and accuracy, achieving fast and accurate detection of individual pigs for “on-device” pig monitoring applications is very challenging. Therefore, in this paper, we propose a method for the fast detection of individual pigs by reducing the computational workload of 3 × 3 convolution in widely-used, deep learning-based object detectors. Then, in order to recover the accuracy of the “light-weight” deep learning-based object detector, we generate a three-channel composite image as its input image, through “simple” image preprocessing techniques. Our experimental results on an NVIDIA Jetson Nano embedded board show that the proposed method can improve the integrated performance of both execution speed and accuracy of widely-used, deep learning-based object detectors, by a factor of up to 8.7.

Field-Applicable Pig Anomaly Detection System Using Vocalization for Embedded Board Implementations

“…However, the remaining three experiments are the result of applying the filter clustering technique to the trained model of the basic structure of MnasNet. In the order of listing, the first experiment uses the model resulting from applying the initial filter clustering algorithm [29], the second one uses the result of applying the 8-bit filter clustering technique to only the convolutional layer comprising 3 × 3 filters of the MnasNet, and the last one uses the model resulting from applying the 8-bit filter clustering technique to all layers of MnasNet to identify abnormalities in pig sounds. The experimental results indicated that when DM was set to 0.75 or 0.5, the model's identification performance could not be maintained because the results showed a significant drop.…”

“…The CNN algorithm is considered an important breakthrough in the image classification field, and the application of models based on it showed a remarkable increase in image recognition performance. This resulted in the CNN algorithm being employed in various fields of study [27][28][29][30]. Recently, different attempts to run such high-performance CNN models in a low-computing environment such as mobile ones have been reported [31,32].…”

“…Recently, there has been a study that, instead of using the algorithm with the DM described earlier, which removes filters at a fixed rate before training the CNN-based deep learning model, applied a clustering method to remove filters of low importance among the ones present at the level of each layer of the trained neural network model [29]. This clustering method was first applied to the detector You Only Look Once (YOLO) [40], and the results proved that the network size was effectively reduced while the identification performance was maintained.…”

“…This clustering method was first applied to the detector You Only Look Once (YOLO) [40], and the results proved that the network size was effectively reduced while the identification performance was maintained. In this study, an 8-bit filter clustering algorithm is proposed to further improve the model compression ratio of the filter clustering algorithm proposed in [29], which relied on a 9-bit filter, while maintaining the detection performance. The algorithm proceeds in the following order:…”

Practices and Applications of Convolutional Neural Network-Based Computer Vision Systems in Animal Farming: A Review

“…NVIDIA Quadro series were also used previously but may not be recommended, because their price was close to that of NVIDIA GeForce GTX 1080 TI while number of CUDA cores, FPP, and MMB were lower than the latter. NVIDIA Jetson series may not outperform other GPUs with regard to the specifications listed in Table 1 , but they were cheap, lightweight, and suitable to be installed onto UAVs or robots [ 89 ], which can help to inspect animals dynamically. Some research trained and tested some lightweight CNN architectures using CPU only [ 64 , 105 , 106 , 107 ], which is not recommended because training process was extremely slow and researchers may spend long time receiving feedback and making decision modifications [ 108 ].…”