Classification methods of a small sample target object in the sky based on the higher layer visualizing feature and transfer learning deep networks

Abstract

The effective classification methods of the small target objects in the no-fly zone are of great significance to ensure safety in the no-fly zone. But, due to the differences of the color and texture for the small target objects in the sky, this may be unobvious, such as the birds, unmanned aerial vehicles (UAVs), and kites. In this paper, we introduced the higher layer visualizing feature extraction method based on the hybrid deep network model to obtain the higher layer feature through combining the Sparse Autoencoder (SAE) model, the Convolutional Neural Network (CNN) model, and the regression classifier model to classify the different types of the target object images. In addition, because the sample numbers of the small sample target objects in the sky may be not sufficient, we cannot obtain much more local features directly to realize the classification of the target objects based on the higher layer visualizing feature extraction; we introduced the transfer learning in the SAE model to gain the cross-domain higher layer local visualizing features and sent the cross-domain higher layer local visualizing features and the images of the target-domain small sample object images into the CNN model, to acquire the global visualizing features of the target objects. Experimental results have shown that the higher layer visualizing feature extraction and the transfer learning deep networks are effective for the classification of small sample target objects in the sky.

Adaptive Inception Based on Transfer Learning for Effective Visual Recognition

“…In this section, the performance of Inception based TL method is compared with existing technique in terms of all the parameters, which is shown in Table 2. Y. Chen, H. Meng, X. Wen, P. Ma, Y. Qin, Z. Ma, and Z. Liu [23] designed a hybrid deep network model to extract the higher layer visualizing features using the combination of SAE, CNN and regression model. The TL was introduced in SAE model for obtaining the crossdomain higher-level features to classify the targetdomain sample objects.…”

Application of deep brief network in transmission spectroscopy detection of pesticide residues in lettuce leaves

“…After DBN training is finished, the following equation is used to extract high‐layer features (Chen et al, ): where b ′ and refers to the transposition of bias of hidden layer and weight between the h n − 1 RBM, respectively, after fine‐tuning and h n represents feature after extraction of DBN.…”