Search Results for author: Joyce Farrell

Found 10 papers, 4 papers with code

Using simulation to quantify the performance of automotive perception systems

no code implementations2 Mar 2023 Zhenyi Liu, Devesh Shah, Alireza Rahimpour, Devesh Upadhyay, Joyce Farrell, Brian A Wandell

The simulation can be used to characterize system performance or to test its performance under conditions that are difficult to measure (e. g., nighttime for automotive perception systems).

object-detection Object Detection

Ray-transfer functions for camera simulation of 3D scenes with hidden lens design

1 code implementation17 Feb 2022 Thomas Goossens, Zheng Lyu, Jamyuen Ko, Gordon Wan, Joyce Farrell, Brian Wandell

Combining image sensor simulation tools (e. g., ISETCam) with physically based ray tracing (e. g., PBRT) offers possibilities for designing and evaluating novel imaging systems as well as for synthesizing physically accurate, labeled images for machine learning.


ISETAuto: Detecting vehicles with depth and radiance information

no code implementations6 Jan 2021 Zhenyi Liu, Joyce Farrell, Brian Wandell

(1) When the spatial sampling resolution of the depth map and radiance image are equal to typical camera resolutions, a ResNet detects vehicles at higher average precision from depth than radiance.

Autonomous Driving

Neural Network Generalization: The impact of camera parameters

no code implementations8 Dec 2019 Zhenyi Liu, Trisha Lian, Joyce Farrell, Brian Wandell

We quantify the generalization of a convolutional neural network (CNN) trained to identify cars.


Soft Prototyping Camera Designs for Car Detection Based on a Convolutional Neural Network

1 code implementation24 Oct 2019 Zhenyi Liu, Trisha Lian, Joyce Farrell, Brian Wandell

It is better to evaluate camera designs for CNN applications using soft prototyping with task-specific metrics rather than consumer photography metrics.

Demosaicking object-detection +1

Designing Illuminant Spectral Power Distributions for Surface Classification

1 code implementation CVPR 2017 Henryk Blasinski, Joyce Farrell, Brian Wandell

There are many scientific, medical and industrial imaging applications where users have full control of the scene illumination and color reproduction is not the primary objective For example, it is possible to co-design sensors and spectral illumination in order to classify and detect changes in biological tissues, organic and inorganic materials, and object surface properties.

Classification Dimensionality Reduction +1

Learning the image processing pipeline

no code implementations30 May 2016 Haomiao Jiang, Qiyuan Tian, Joyce Farrell, Brian Wandell

Many creative ideas are being proposed for image sensor designs, and these may be useful in applications ranging from consumer photography to computer vision.

Simultaneous Surface Reflectance and Fluorescence Spectra Estimation

1 code implementation13 May 2016 Henryk Blasinski, Joyce Farrell, Brian Wandell

There is widespread interest in estimating the fluorescence properties of natural materials in an image.

Cannot find the paper you are looking for? You can Submit a new open access paper.