Hidekazu Iwaki

Distributed and lightweight multi-camera human activity classification

We propose a human activity classification algorithm that has a distributed and lightweight implementation appropriate for wireless camera networks. With input from multiple cameras, our algorithm achieves invariance to the orientation of the actor and to the camera viewpoint. We conceptually describe how the algorithm can be implemented on a distributed architecture, obviating the need for centralized processing of the entire multi-camera data. The lightweight implementation is made possible by the very affordable memory and communication bandwidth requirements of the algorithm. Notwithstanding its lightweight nature, the performance of the algorithm is comparable to that of the earlier multi-camera approaches that are based on computationally expensive 3D human model construction, silhouette matching using reprojected 2D views, and so on. Our algorithm is based on multi-view spatio-temporal histogram features obtained directly from acquired images; no background subtraction is required. Results are analyzed for two publicly available multi-camera multi-action datasets. The systems advantages relative to single camera techniques are also discussed.

Online distributed calibration of a large network of wireless cameras using dynamic clustering

We present a cluster-based distributed algorithm for calibrating large networks of wireless cameras. Due to the complex nature of sensing modality of a camera sensor, the work presented here differs significantly from the previous localization methods. Our system does not require any beacon nodes; it only utilizes object features of moving objects in the scene extracted from image sequences. The algorithm is fully distributed, and the localization estimates can be improved as more object features are acquired in the network. We show simulations of our system using a graphical simulator we developed specifically for wireless camera sensor networks. Early results indicate that our system is capable of localizing a large network of cameras in an energy-efficient way.

A novel evidence accumulation framework for robust multi-camera person detection

We propose a novel evidence accumulation framework that accurately estimates the positions of humans in a 3D environment. The framework consists of a network of distributed agents having different functionalities. The modular structure of the network allows scalability to large surveillance areas and robust operation. The framework does not assume reliable measurements in single cameras (referred to as dasiasensing agentspsila in our framework) or reliable communication between different agents. There is a position uncertainty associated with single camera measurements and it is reduced through an uncertainty reducing transform that performs evidence accumulation using multiple camera measurements. Our framework has the advantage that single camera measurements do not need to be temporally synchronized to perform evidence accumulation. The system has been tested for detecting single and multiple humans in the environment. We conducted experiments to evaluate the localization accuracy of the position estimates obtained from the system by comparing them with the ground truth. Also, two different configurations of the agents were tested to compare their detection performance.

A particle filter framework using optimal importance function for protein molecules tracking

Tagging and tracking protein molecules are a key to a better understanding of proteomics in diverse aspects. In this paper, a common framework of particle filter using optimal importance function is proposed for confocal protein molecules tracking. To deal with the challenges stemming from small size, deformable shape, noisy environment, and multi-modality motion, a stochastic process based particle filter is used. Partial Gaussian state space (PGSS) model is developed as the importance function to incorporate the latest measurement in the state estimation. Experimental results have demonstrated the performance of the proposed algorithm for both Brownian and translational motion.

Motion detection for subcellular structure trafficking

A detailed understanding of subcellular structure motility is critical to understanding how cells regulate the delivery of specific proteins from the site of synthesis to the site of action. Diverse modalities have been observed for subcellular dynamics, such as directional movement, random movement, tethered movement, object appearing, and disappearing. Motion modality detection is important for efficient subcelluar structure tracking and population study. In this paper, we present a new technique, called “divergence filter,” for detecting subcellular structure motion modalities. The plausibility of the efficient technique was applied to caveolar membrane trafficking sequences obtained using confocal microscopy.