2018 Harvest Imaging Forum Agenda

Albert Theuwissen announces agenda of Harvest Imaging Forum, to be held on December 6-7 in Delft, the Netherlands.

Day 1 of the forum is devoted to "Efficient embedded deep learning for vision applications," presented by Marian VERHELST (KU Leuven, Belgium):

1. Introduction into deep learning
   From neural networks (NN) to deep NN
   Benefits & applications
   Training and inference with deep NN
   Types of deep NN
   Sparse connectivity
   Residual networks
   Separable models
   Key enablers & challenges
2. Computer architectures for deep NN inference
   Benefits and limitations of CPU and GPUs
   Exploiting NN structure in custom processors
   Architecture level exploitation: spatial reuse in efficient datapaths
   Architecture level exploitation: temporal reuse in efficient memory hierarchies
   Circuit level exploitation: near/in memory compute
   Exploiting NN precision in custom processors
   Architecture level exploitation: reduced and variable precision processors
   Circuit level exploitation: mixed signal neural network processors
   Exploiting NN sparsity:
   Architecture level exploitation: computational and memory gating
   Architecture level exploitation: I/O compression
3. HW and SW optimization for efficient inference
   Co-optimizing NN topology and precision with hardware architectures
   Hardware modeling
   Hardware-aware network optimization
   Network-aware hardware optimization
4. Trends and outlook
   Dynamic application-pipelines
   Dynamic SoCs
   Beyond deep learning, explainable AI
   Outlook

Day 2 is devoted to "Image and Data Fusion," presented by Wilfried PHILIPS (imec and Ghent University, Belgium):

1. Data fusion: principles and theory
   Bayesian estimation
   Priors and likelihood
   Information content, redundancy, correlation
   Application to image processing: recursive maximum likelihood tracking, pixel fusion
2. Pixel level fusion
   Sampling grids and spatio-temporal aliasing
   Multi-modal sensors, interpolation
   Temporal fusion and superresolution
   Multi-focal fusion
3. Multi-camera image fusion
   Occlusion and inpainting
   Uni and multimodal Inter-camera pixel fusion
   Fusion of heterogeneous sources: camera, lidar, radar
   Applications: time of flight, hyperspectral, hdr, multiview imaging
   Fusion of heterogeneous sources: radar, video, lidar
4. Geometric fusion
   Multi-view geometry
   Fusion of point clouds
   Image stitching
   Simultaneous localization and mapping
   Applications: remote sensing from drones and vehicles
5. Inference fusion in camera networks
   Multi-camera calibration
   Occlusion reasoning for multiple cameras with an overlapping viewpoint
   Multi-camera tracking
   Cooperative fusion and distributed processing