In this paper we present Hyper-Dimensional Reconfigurable Analytics at the Tactical Edge using low-SWaP embedded hardware that can perform real-time reconfiguration at the edge leveraging non-MAC deep neural nets (DNN) combined with hyperdimensional (HD) computing accelerators.
We review HyDRATE, a low-SWaP reconfigurable neural network architecture developed under the DARPA AIE HyDDENN (Hyper-Dimensional Data Enabled Neural Network) program.
We present a camera system for instantaneous, non-destructive capture of spectral signatures for forensic analysis. Our system detects highly probative samples in the forensic scene mixed by the multiple target objects by combining a coded aperture snapshot spectral imager with a multi-spectral detection algorithm. An Adaptive Cosine Estimator (ACE) is used to quantitatively detect and classify the probative samples from the decoded spectral datacube. In this paper, we demonstrate selected results using our system for luminescence characteristics and spectral classification of a number of samples.
Full motion video (FMV) in unreliable, low-bit rate network channels suffers from quality issues such as jitter and block artifacts. In this paper, we introduce Vision Guided Compression (VGC), as a pre-processing technology that can be coupled with standards-based video coding, to provide FMV at low-bit rates. VGC utilizes computer vision algorithms to track salient features and keep them sharp, while non-salient features are lowpass filtered. With this approach, VGC provides an additional spatial parameter to gracefully tune the QoS, while providing FMV and preserving salient visual information.
We introduce Salience-Based Compression (SBC), a vision-guided pre-filtering technology, coupled with standards-based video coding. SBC works by detecting and tracking salient features and keeping them sharp; non-salient features are lowpass filtered, causing an automatic and beneficial drop in bit rate. Because salience-based pre-filtering is performed as a pre-processing step, it can interface to any COTS video encoder, thus enabling use in existing infrastructures and ensuring the compliance of the video bitstream that is produced. For typical aerial surveillance video, SBC can reduce bit rate by up to a factor of four, yet still provide full motion video (FMV) and preserve salient visual information.
Maximizing transmitted video quality at the highest resolution and highest frame rate is desirable ,but multiple approaches can be employed to
maximize transmission quality for the video at a given bitrate.
The current state-of-the-art video coding standard, H.264, offers substantially better compression performance than earlier video coding standards. However, even with these gains, better compression is still desirable. This paper describes a macroblock-based mixed resolution video encoding system. By reducing the spatial resolution of some macroblock residuals intelligently, our preliminary experiments show up to 20% improvement in video compression efficiency compared to H.264 while maintaining good subjective video quality.
In this paper, we present the work on implementation of a half-D1interlaced MPEG-4 encoder with Equator Technology DSP chip, BSP-15. The BSP-15 DSP consists mainly of a VLIW core, Co-processors, and media I/O interfaces. The encoder utilizes several BSP-15 functional blocks in parallel. In general, the VLIW performs pixel procesing that is computationally intensive. The VLx coprocessor completes variable length coding. Further parallelism is obtained by pre-loading data cache and doubling data buffers. Given the DSP processing power and real time requirements, a complexity control scheme is implemented. A frame-level quantization scheme with quality and rate control is employed. The current implementation for video at 30 fps consumes about 90% of the chip performance at a bit rate ~2Mbps.
In this paper, we propose a spatial, temporal and histogram (STH) registration algorithm for video sequences. This algorithm is developed based on a frame-level model of the misalignments often introduced by video processing algorithms, such as compression, frame rate conversion or by video capturing. With this model, the STH registration is formulated as a constrained minimization of a matching cost, and it is solved using dynamic programming. In addition, prior information about the application is incorporated in the form of contextual cost. Experimental results on both synthetic and real processed video sequences have shown that the proposed algorithm is effective and robust to a wide range of noises. In addition, we successfully applied this algorithm to digital forensic watermark detection.