A lightweight deep network image target detection method applicable to Raspberry Pi belongs to the field of deep learning and target detection, and comprises the following steps: firstly, collecting an image containing a to-be-detected target, and preprocessing the collected image for network training; secondly, inputting the preprocessed image into a depth separable expansion convolutional neural network for feature extraction to obtain feature maps with different resolutions; inputting the feature maps with different resolutions into a feature pyramid network for feature fusion, and generating a fusion feature map carrying richer information; and then carrying out classification and positioning of a to-be-detected target on the fusion feature map by adopting a detection network, and finally carrying out non-maximum suppression to obtain an optimal target detection result. The image target detection method based on the deep neural network overcomes the difficulties that the image target detection method based on the deep neural network is difficult to realize on the Raspberry Pi platform and the image target detection method based on the lightweight network is low in detection accuracy on the Raspberry Pi platform.

Lightweight deep network image target detection method suitable for Raspberry Pi

Disclosed is an outdoor non-fixed scene weather identification method based on deep learning. The method comprises the steps of: constructing a basic structure of a lightweight convolutional neural network; collecting pictures of various types of weather and making the pictures into a data set in a specific format; training the lightweight convolutional neural network by using the data set; and transplanting the trained lightweight convolutional neural network into an embedded platform or a mobile device, taking a photographed weather picture as an input of the lightweight convolutional neural network, and outputting probabilities corresponding to various weather conditions. By means of the present invention, the defect of only being able to identify the weather in a fixed scene by means of a traditional method is overcome, and since a calculated amount is very small, the present invention can be applied to an embedded platform or a mobile device and is very high in practicability.

Outdoor non-fixed scene weather identification method based on deep learning

The invention discloses an image classification model based on hybrid depth separable expansion convolution. The construction process comprises the steps that a depth separable expansion convolution layer, a feature information splicing layer, a convolution layer, a batch standardization layer and a correction linear unit layer are packaged into a hybrid depth separable expansion convolution module from front to back; the convolution layer, the batch normalization layer, the correction linear unit layer, the mixed depth separable expansion convolution module, the maximum value pooling layer, the flattening layer, the random inactivation layer and the full connection layer are packaged from front to back to form a backbone network of the deep neural network; the process also includes randomly initializing the parameter weight of the backbone network, and presetting the number of iterations and the momentum parameter of the batch normalization layer; and optimizing parameters of the network model by adopting a stochastic gradient descent method, and repeating iterative computation until a loss value is converged to obtain an optimal network model. By means of the scheme, the method has the advantages of being simple in structure, small in calculation workload, accurate in classification and the like.

Image classification model based on hybrid depth separable expansion convolution and classification method thereof

The invention relates to a high-precision image semantic segmentation algorithm model and a segmentation method. The model is used for modeling the detail uncertainty of the target for the loss of global information in a multi-stage fusion process, and can eliminate the detail uncertainty caused by image noise interference and less local information of the image to a great extent, thereby improving the semantic segmentation precision of the target edge. The segmentation method is realized based on the segmentation algorithm model. According to the segmentation method, the difficulty of detailfeature identification of the convolutional neural network is reduced, the detail modeling capability and modeling precision of the convolutional neural network are improved, the detail structure andfeatures of the target can be effectively identified, and the interference of shielding, image quality and other factors on semantic segmentation is reduced.

High-precision image semantic segmentation algorithm model and segmentation method

The invention discloses a remote sensing image ship target detection method based on a sparse MobileNetV2 network, and belongs to the technical field of remote sensing image ship target detection. Themethod solves the problems that target features are difficult to extract due to ship remote sensing image information redundancy, and satellite in-orbit real-time analysis is difficult due to the contradiction between large remote sensing image data information amount and weak in-orbit calculation processing capability. The method comprises the following steps: carrying out overlapping segmentation and downsampling processing on a remote sensing image to obtain an image block after downsampling; using the down-sampled image blocks to train the seven sets of convolution layers, using the imageblocks in the overlapped and segmented images to train the pruned MobileNetV2 network, and obtaining the trained sparse MobileNetV2 network when the maximum number of iterations is achieved; and carrying out target detection on the to-be-detected remote sensing image by using the trained sparse MobileNetV2 network. The method can be applied to the technical field of remote sensing image ship target detection.

Remote sensing image ship target detection method based on sparse MobileNetV2 network

The invention discloses a method based on D. MobileNet (Dilated-Mobilenet) neural network image classification method. By combining hole convolution with MobileNet and improving the convolution kernelreceptive field of high-resolution input layer, the quality of output features is improved, and the number of network parameters is not increased, so that the network structure can improve classification accuracy. The method comprises the following steps: 1) preparing a data set; 2) building a MobileNet network; 3) building D-MobileNet network; 4) setting up super parameter. After the model is trained, the pictures of the verification set are verified by the trained convolution neural network model, and classification prediction is complete. The experimental result shows that the invention can obtain better classification accuracy than the MobileNet network.

D-MobileNet-based neural network image classification method

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Wang Xin

Author Tools

Chat about Author

Papers

D-MobileNet-based neural network image classification method