{"id":6479,"date":"2024-01-10T16:49:18","date_gmt":"2024-01-10T08:49:18","guid":{"rendered":"https:\/\/ascendas-asia.com\/?page_id=6479"},"modified":"2024-01-10T17:05:26","modified_gmt":"2024-01-10T09:05:26","slug":"ai-for-radar-2","status":"publish","type":"page","link":"https:\/\/ascendas-asia.com\/th\/ai-for-radar-2\/","title":{"rendered":"AI for Radar"},"content":{"rendered":"\n\n\n
\n

Apply artificial intelligence techniques to radar applications<\/strong><\/h2>\n

\n

<\/h1>\n
\n

<\/p>\n\n\n\n
\n

Simulate radar signals to train machine and deep learning models for target and signal classification.\u200b<\/p>\n

With MATLAB®<\/sup> <\/span>and Simulink®<\/sup>, you can:<\/p>\n

    \n
  • Label signals collected from radar systems using the Signal Labeler app<\/li>\n
  • Augment datasets by simulating radar waveforms and echoes from objects with a range of radar cross sections\u200b<\/li>\n
  • Simulate micro-Doppler signatures of hand gestures and animated objects with non-rigid bodies such as helicopters, pedestrians, and bicyclists<\/li>\n
  • Apply identification and classification workflows to public datasets<\/li>\n<\/ul>\n<\/td>\n
\n<\/td>\n\"\"<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

<\/h1>\n

Why use AI for Radar?<\/strong><\/h2>\n

Synthesize radar signals to train machine and deep learning models for target and signal classification and apply AI techniques to data collected from radar systems.<\/span>
<\/span><\/p>\n

<\/h2>\n\n\n\n\n\n\n\n\n\n\n\n\n
\"\"<\/td>\n<\/td>\n\"\"<\/td>\n<\/tr>\n
<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
\n

Waveform Classification and Spectrum Sensing<\/span><\/h3>\n

Synthesize and label radar waveforms to train deep learning networks.  Extract time-frequency features from signals and perform waveform modulation classification using deep learning networks. Determine bandwidth of occupied signals.<\/p>\n<\/td>\n

<\/td>\n\n

Radar Target Classification<\/span><\/h3>\n

Classify radar returns based on radar cross sections with both machine and deep learning approaches. The machine learning approach uses wavelet scattering feature extraction coupled with a support vector machine. Two common deep learning approaches are transfer learning using SqueezeNet and a Long Short-Term Memory (LSTM) recurrent neural network.<\/p>\n<\/td>\n<\/tr>\n

\n

 <\/span><\/h3>\n<\/td>\n

<\/td>\n\n

 <\/span><\/h3>\n<\/td>\n<\/tr>\n

\n

\"\"
<\/span><\/h3>\n<\/td>\n

<\/td>\n\n

\n

Hand Gesture Classification<\/span><\/h3>\n

Classify ultra-wideband (UWB) impulse radar signal data from a publicly available dataset of dynamic hand gestures. Use a multiple-input, single-output convolutional neural network (CNN) where the CNN model extracts feature information from each signal before combining it to make a final gesture label prediction.<\/span><\/p>\n<\/td>\n

<\/td>\n\n

Micro-Doppler Signature Classification\u200b<\/span><\/h3>\n

Classify pedestrians and bicyclists based on their micro-Doppler characteristics using time-frequency analysis and a deep learning network. The movements of different parts of an object placed in front of a radar produce micro-Doppler signatures that can be used to identify the object. <\/span><\/p>\n<\/td>\n<\/tr>\n

\n

<\/h2>\n<\/td>\n

<\/td>\n\n

<\/h2>\n<\/td>\n<\/tr>\n

\n

\"\"<\/h2>\n<\/td>\n

<\/td>\n\n

 \"\"<\/h2>\n<\/td>\n<\/tr>\n

\n

SAR Image Classification<\/span><\/h3>\n

Use deep learning techniques for target classification of Synthetic Aperture Radar (SAR) images. Create and train a Convolution Neural Network (CNN) to classify SAR targets from the Moving and Stationary Target Acquisition and Recognition (MSTAR) Mixed Targets dataset.<\/p>\n<\/td>\n

<\/td>\n\n

SAR Image Recognition<\/span><\/h3>\n

Perform target recognition of Synthetic Aperture Radar (SAR) images using a Region-based Convolutional Neural Networks (R-CNN). The R-CNN network integrates detection and recognition with efficient performance that scales to large scene SAR images.<\/p>\n<\/td>\n<\/tr>\n

\n

<\/h2>\n<\/td>\n

<\/td>\n\n

<\/h2>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

<\/h1>\n

Using AI for Radar with MATLAB<\/strong><\/h2>\n\n\n\n\n
\n

\"\"<\/p>\n<\/td>\n

<\/td>\n\"\"<\/td>\n<\/tr>\n
[White paper] Deep Learning Using Synthesized Data for Communications and Radar<\/a><\/strong><\/td>\n<\/td>\nAnalyzing Satellite Radar Imagery with Deep Learning<\/a><\/strong><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

\n

<\/h1>\n

Products Used<\/strong><\/span><\/h2>\n