Deep Learning Based Target Tracking and Classification for Infrared Videos Using Compressive Measurements

Although compressive measurements save data storage and bandwidth usage, they are difficult to be used directly for target tracking and classification without pixel reconstruction. This is because the Gaussian random matrix destroys the target location information in the original video frames. This paper summarizes our research effort on target tracking and classification directly in the compressive measurement domain. We focus on one particular type of compressive measurement using pixel subsampling. That is, original pixels in video frames are randomly subsampled. Even in such a special compressive sensing setting, conventional trackers do not work in a satisfactory manner. We propose a deep learning approach that integrates YOLO (You Only Look Once) and ResNet (residual network) for multiple target tracking and classification. YOLO is used for multiple target tracking and ResNet is for target classification. Extensive experiments using short wave infrared (SWIR), mid-wave infrared (MWIR), and long-wave infrared (LWIR) videos demonstrated the efficacy of the proposed approach even though the training data are very scarce.

New Results in Perceptually Lossless Compression of Hyperspectral Images

Hyperspectral images (HSI) have hundreds of bands, which impose heavy burden on data storage and transmission bandwidth. Quite a few compression techniques have been explored for HSI in the past decades. One high performing technique is the combination of principal component analysis (PCA) and JPEG-2000 (J2K). However, since there are several new compression codecs developed after J2K in the past 15 years, it is worthwhile to revisit this research area and investigate if there are better techniques for HSI compression. In this paper, we present some new results in HSI compression. We aim at perceptually lossless compression of HSI. Perceptually lossless means that the decompressed HSI data cube has a performance metric near 40 dBs in terms of peak-signal-to-noise ratio (PSNR) or human visual system (HVS) based metrics. The key idea is to compare several combinations of PCA and video/ image codecs. Three representative HSI data cubes were used in our studies. Four video/image codecs, including J2K, X264, X265, and Daala, have been investigated and four performance metrics were used in our comparative studies. Moreover, some alternative techniques such as video, split band, and PCA only approaches were also compared. It was observed that the combination of PCA and X264 yielded the best performance in terms of compression performance and computational complexity. In some cases, the PCA + X264 combination achieved more than 3 dBs than the PCA + J2K combination.

Perceptually Lossless Compression for Mastcam Multispectral Images: A Comparative Study

The two mast cameras, Mastcams, onboard Mars rover Curiosity are multispectral imagers with nine bands in each. Currently, the images are compressed losslessly using JPEG, which can achieve only two to three times of compression. We present a comparative study of four approaches to compressing multispectral Mastcam images. The first approach is to divide the nine bands into three groups with each group having three bands. Since the multispectral bands have strong correlation, we treat the three groups of images as video frames. We call this approach the Video approach. The second approach is to compress each group separately and we call it the split band (SB) approach. The third one is to apply a two-step approach in which the first step uses principal component analysis (PCA) to compress a nine-band image cube to six bands and a second step compresses the six PCA bands using conventional codecs. The fourth one is to apply PCA only. In addition, we also present subjective and objective assessment results for compressing RGB images because RGB images have been used for stereo and disparity map generation. Five well-known compression codecs, including JPEG, JPEG-2000 (J2K), X264, X265, and Daala in the literature, have been applied and compared in each approach. The performance of different algorithms was assessed using four well-known performance metrics. Two are conventional and another two are known to have good correlation with human perception. Extensive experiments using actual Mastcam images have been performed to demonstrate the various approaches. We observed that perceptually lossless compression can be achieved at 10:1 compression ratio. In particular, the performance gain of the SB approach with Daala is at least 5 dBs in terms peak signal-to-noise ratio (PSNR) at 10:1 compression ratio over that of JPEG. Subjective comparisons also corroborated with the objective metrics in that perceptually lossless compression can be achieved even at 20 to 1 compression.

Target Tracking and Classification Using Compressive Measurements of MWIR and LWIR Coded Aperture Cameras

Pixel-wise Code Exposure (PCE) camera is one type of compressive sensing camera that has low power consumption and high compression ratio. Moreover, a PCE camera can control individual pixel exposure time that can enable high dynamic range. Conventional approaches of using PCE camera involve a time consuming and lossy process to reconstruct the original frames and then use those frames for target tracking and classification. In this paper, we present a deep learning approach that directly performs target tracking and classification in the compressive measurement domain without any frame reconstruction. Our approach has two parts: tracking and classification. The tracking has been done using YOLO (You Only Look Once) and the classification is achieved using Residual Network (ResNet). Extensive experiments using mid-wave infrared (MWIR) and long-wave infrared (LWIR) videos demonstrated the efficacy of our proposed approach.

A new approach to solar flare prediction

All three components of the current density are required to compute the heating rate due to free magnetic energy dissipation.Here we present a first test of a new model developed to determine if the times of increases in the resistive heating rate in active region(AR)photospheres are correlated with the subsequent occurrence of M and X flares in the corona.A data driven,3D,non-force-free magnetohydrodynamic model restricted to the near-photospheric region is used to compute time series of the complete current density and the resistive heating rate per unit volume[Q(t)]in each pixel in neutral line regions(NLRs)of 14 ARs.The model is driven by time series of the magnetic field B measured by the Helioseismic&Magnetic Imager on the Solar Dynamics Observatory(SDO)satellite.Spurious Doppler periods due to SDO orbital motion are filtered out of the time series for B in every AR pixel.For each AR,the cumulative distribution function(CDF)of the values of the NLR area integral Qi(t)of Q(t)is found to be a scale invariant power law distribution essentially identical to the observed CDF for the total energy released in coronal flares.This suggests that coronal flares and the photospheric Qi are correlated,and powered by the same process.The model predicts spikes in Qi with values orders of magnitude above background values.These spikes are driven by spikes in the non-force free component of the current density.The times of these spikes are plausibly correlated with times of subsequent M or X flares a few hours to a few days later.The spikes occur on granulation scales,and may be signatures of heating in horizontal current sheets.It is also found that the times of relatively large values of the rate of change of the NLR unsigned magnetic flux are also plausibly correlated with the times of subsequent M and X flares,and spikes in Qi.