arXiv subjects

Yasamin Mostofi

Publications and source records attributed to Yasamin Mostofi.

23 records · Page 2Linked to original sources

arXiv2018

PieAPP: Perceptual Image-Error Assessment through Pairwise Preference

The ability to estimate the perceptual error between images is an important problem in computer vision with many applications. Although it has been studied extensively, however, no method currently exists that can robustly predict visual differences like humans. Some previous approaches used hand-coded models, but they fail to model the complexity of the human visual system. Others used machine learning to train models on human-labeled datasets, but creating large, high-quality datasets is difficult because people are unable to assign consistent error labels to distorted images. In this paper, we present a new learning-based method that is the first to predict perceptual image error like human observers. Since it is much easier for people to compare two given images and identify the one more similar to a reference than to assign quality scores to each, we propose a new, large-scale dataset labeled with the probability that humans will prefer one image over another. We then train a deep-learning model using a novel, pairwise-learning framework to predict the preference of one distorted image over the other. Our key observation is that our trained network can then be used separately with only one distorted image and a reference to predict its perceptual error, without ever being trained on explicit human perceptual-error labels. The perceptual error estimated by our new metric, PieAPP, is well-correlated with human opinion. Furthermore, it significantly outperforms existing algorithms, beating the state-of-the-art by almost 3x on our test set in terms of binary error rate, while also generalizing to new kinds of distortions, unlike previous learning-based methods.

cs.CV↗

arXiv2018

Passive Crowd Speed Estimation in Adjacent Regions With Minimal WiFi Sensing

In this paper, we propose a methodology for estimating the crowd speed using WiFi devices without relying on people to carry any device. Our approach not only enables speed estimation in the region where WiFi links are, but also in the adjacent possibly WiFi-free regions. More specifically, we use a pair of WiFi links in one region, whose RSSI measurements are then used to estimate the crowd speed, not only in this region, but also in adjacent WiFi-free regions. We first prove how the cross-correlation and the probability of crossing the two links implicitly carry key information about the pedestrian speeds and develop a mathematical model to relate them to pedestrian speeds. We then validate our approach with 108 experiments, in both indoor and outdoor, where up to 10 people walk in two adjacent areas, with variety of speeds per region, showing that our framework can accurately estimate these speeds with only a pair of WiFi links in one region. For instance, the NMSE over all experiments is 0.18. We also evaluate our framework in a museum-type setting and estimate the popularity of different exhibits. We finally run experiments in an aisle in Costco, estimating key attributes of buyers' behaviors.

eess.SP↗

arXiv2017

Crowd Counting Through Walls Using WiFi

Counting the number of people inside a building, from outside and without entering the building, is crucial for many applications. In this paper, we are interested in counting the total number of people walking inside a building (or in general behind walls), using readily-deployable WiFi transceivers that are installed outside the building, and only based on WiFi RSSI measurements. The key observation of the paper is that the inter-event times, corresponding to the dip events of the received signal, are fairly robust to the attenuation through walls (for instance as compared to the exact dip values). We then propose a methodology that can extract the total number of people from the inter-event times. More specifically, we first show how to characterize the wireless received power measurements as a superposition of renewal-type processes. By borrowing theories from the renewal-process literature, we then show how the probability mass function of the inter-event times carries vital information on the number of people. We validate our framework with 44 experiments in five different areas on our campus (3 classrooms, a conference room, and a hallway), using only one WiFi transmitter and receiver installed outside of the building, and for up to and including 20 people. Our experiments further include areas with different wall materials, such as concrete, plaster, and wood, to validate the robustness of the proposed approach. Overall, our results show that our approach can estimate the total number of people behind the walls with a high accuracy while minimizing the need for prior calibrations.

eess.SP↗

arXiv2016

Motion and Communication Co-optimization with Path Planning and Online Channel Estimation

This paper considers the problem of optimally balancing motion energy and communication transmission energy of a mobile robot tasked with transmitting a given number of data bits to a remote station, while navigating to a prespecified destination in a given amount of time. The problem is cast in the setting of optimal control, where the robot has to choose its path, acceleration, and transmission rate along the path so as to minimize its energy required for transmission and motion, while satisfying various power and communication constraints. We use realistic models for the robot's channel estimation, motion dynamics, and power and energy costs. The main contribution of the paper is to show how to co-optimize robot's path along with other communication and motion variables. Two versions of the problem are solved: the first is defined offline by assuming that all the channel measurements are taken before the robots starts moving, while in the second the channel estimation is updated while the robot is in motion, and hence it is solved online. In both cases we utilize an in-house algorithm that computes near-optimal solutions in little time, which enables its use in the online setting. The optimization strategy is described in detail and validated by simulation of realistic scenarios.

math.OC↗

arXiv2014

Binary Log-Linear Learning with Stochastic Communication Links

In this paper, we consider distributed decision-making over stochastic communication links in multi-agent systems. We show how to extend the current literature on potential games with binary log-linear learning (which mainly focuses on ideal communication links) to consider the impact of stochastic communication channels. More specifically, we derive conditions on the probability of link connectivity to achieve a target probability for the set of potential maximizers (in the stationary distribution). Furthermore, our toy example demonstrates a transition phenomenon for achieving any target probability for the set of potential maximizers.

cs.MA↗