Research Projects
Selected systems and research work — most recent first.
End-to-end distributed training and inference pipeline for high-resolution surface inspection. Custom CUDA preprocessing, multi-node training with near-linear scaling, TensorRT INT8 deployment on edge devices.
Aggressive image quantization and lossy compression as preprocessing for CNNs — reducing storage and training time with minimal accuracy loss.
Benchmarked 11 CNN architectures on Xilinx ZCU102 FPGA for satellite onboard processing. INT8 quantization via VitisAI, power/throughput profiling.
Reimplemented 12 CNN architectures in TensorFlow with full VitisAI compatibility for FPGA deployment. ImageNet-pretrained weights included.
Novel trajectory distance metric based on Normalized Compression Distance. Bloom filter embeddings compress trajectories to ≤1024 bits with >80% k-NN classification accuracy across real-world datasets.
Parameter-free unsupervised change detection for multispectral and SAR satellite imagery using Kolmogorov complexity approximation. 70,000 km² processed with 36% runtime reduction.