One of the important research directions in the field of target detection in computer vision, among which deep learning-based target detection can extract advanced features and has higher detection accuracy than traditional detection algorithms. The inference speed of convolutional neural networks in embedded platforms is low, and the practical application value is low. Therefore, for the background of optoelectronic device detection and camera detection, on the embedded platform NVIDIA Jeston Nano, the ResNet18 convolutional neural network is used to identify the photoelectric target. Use TensorRT to accelerate the process of network model simplification and engine construction, and accelerate the network inference time. Experimental results show that when the input image resolution is 640*480, the inference time of tensorRT technology after running the network on the NVIDIA Jeston Nano device is in the range of 0.04-0.06s, and the single-area photoelectric target detection inference is accelerated by 2.38 times and the multi-area photoelectric target detection inference is accelerated by 2.74 times, which provides support for practical applications.
Generative adversarial network (GAN) has become a hot research topic in the field of image processing. As an unsupervised training model, GAN has been widely used in the field of computer vision, especially in image style transfer. The purpose of the GAN is to make the generator generate a false image, and the discriminator cannot tell whether the input image is the real image or the generated image. Compared with traditional network models, GAN model has these advantages in image style transfer: GAN is composed of two different networks, and the loss function is automatically learned by playing games with each other. GAN belongs to unsupervised training and does not need to annotate the data set, which saves a lot of work. In this paper, improved GAN models related to image style migration are summarized. Firstly, the principle and method of image style transfer based on convolutional neural network are introduced. Secondly, the status, principle and prospect of GAN are introduced, and the causes of gradient disappearance and mode collapse of GAN are analyzed in detail. On this basis, the principles, advantages and disadvantages of CGAN, DCGAN, CycleGAN and StarGAN V2 network models are introduced. Finally, it summarizes the current problems and future research directions of style transfer based on GAN.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.