Select a calendar:
Filter August Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for August 30, 2016
-
PhD Defense - Jing Huang
Tue, Aug 30, 2016 @ 10:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
University Calendar
Title: Object Detection and Recognition from 3D Point Clouds
Location: PHE 223
Time: 10 am, Tuesday, Aug 30th, 2016
PhD Candidate: Jing Huang
Committee:
Suya You (Chair), Ulrich Neumann, Aiichiro Nakano, C.-C. Jay Kuo (Outside Member)
Abstract:
Object detection and recognition are fundamental problems in computer vision. While most existing works have been in the 2D image domain, 3D data are gaining popularity in recent years thanks to the development of 3D sensors. My work focuses on object detection and recognition from 3D point clouds, which involves various stages of point cloud processing including feature description, matching, segmentation, localization, classification, and labeling. We explore two different strategies to solve the detection and recognition problems:
The first strategy is to compute a set of descriptors on the local neighborhood of feature points and use them in the matching-based framework. We apply this strategy in the industrial object detection problem, where the intra-class variation is small. We first present a 3D descriptor based on the self-similarity property of the data, and apply the descriptor to build a feature-based matching module. The matching module is incorporated in the object detection and recognition system, which is further used to build an object-level change detection system.
The second strategy is to compute a representation for a whole candidate cluster, and then apply machine learning techniques to classify the clusters without knowing the exact poses. We employ this strategy in the urban object detection, where the intra-class variation is much higher. Specifically, we develop a slicing-based localization method for pole-like objects, introduce a representation of six attributes based on the height and five PCA-based features and apply SVM to classify the candidate objects into four categories. For vehicles, the PCA-based features are not enough to tell them apart from other planar objects. To this end, we employ the deep Convolutional Neural Networks (CNN) based on the orthogonal-view information from the candidates, and prior knowledge for vehicles and urban environment is utilized to help the detection process. Finally, inspired by the success of deep learning on the 2D problems, we present the voxel-based fully-3D Convolutional Neural Network on the point cloud labeling problem. This approach minimizes the use of prior knowledge and hand-crafted features compared to most previous approaches.
We demonstrate the proposed object detection and recognition methods through experiments on point clouds from industrial datasets and large-scale urban datasets.
Location: Charles Lee Powell Hall (PHE) - 223
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
AI Seminar
Tue, Aug 30, 2016 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Fei Sha, UCLA
Talk Title: Large-scale Zero-Shot Learning
Abstract: Abstract: Is it possible for computer vision systems to recognize visual object categories that they have never seen before? More precisely, in the paradigm of zero-shot learning, a learner has access to only a subset of the labels in the labeling space (and its associated exemplar images). Nonetheless, our goal for the learner is to recognize future occurrences of images from all possible categories. This is an important research problem with great application potential for automatic object recognition in the wild where the number of possible visual categories continuously rises and there is little hope to collect adequate labeling samples for those categories fast enough.
In this talk, I will describe a few work from my research group on tackling this challenge. We have demonstrated that it is possible to train vision systems on the ImageNet images from 1,000 visual categories yet attaining meaningful results on recognizing a disjoint set of 20,000 visual categories.
This is a joint research work with my PhD students (Soravit Changpinyo and Weilun Chao ) at USC and our collaborator Prof. Boqing Gong (U. of Central Florida).
Host: Emilio Ferrara
Location: Information Science Institute (ISI) - 11th floor Large Conference room
Audiences: Everyone Is Invited
Contact: Kary LAU
-
Microsoft Product Demo & Devices
Tue, Aug 30, 2016 @ 12:00 PM - 02:00 PM
Viterbi School of Engineering Career Connections
Workshops & Infosessions
How does Microsoft design hardware?
What do all of these products have in common?
How does Microsoft take one design and make it into millions?
Find out answers to these questions and many more at Microsoft's Manufacturing & Supply Chain (MSC) and Devices Product Demo Booth. This will be your chance to interact with Microsoft employees and learn about the end to process of taking a product from a design to a product in the customer's hands.
Majors: ME, EE, IE & SCLocation: RTH LOBBY
Audiences: All Viterbi
Contact: RTH 218 Viterbi Career Connections
-
Introduction to Viterbi Gateway Workshop
Tue, Aug 30, 2016 @ 12:30 PM - 01:30 PM
Viterbi School of Engineering Career Connections
Workshops & Infosessions
Come to this presentation to learn how to navigate the Viterbi Career Gateway,a powerful job & internship search tool available ONLY to Viterbi students.
Location: Ronald Tutor Hall of Engineering (RTH) - 211
Audiences: All Viterbi
Contact: RTH 218 Viterbi Career Connections
-
Light Modulators-Figures of Merit
Tue, Aug 30, 2016 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Jacob B Khurgin, Johns Hopkins University
Talk Title: Light Modulators-Figures of Merit
Abstract: We compare characteristics of various modulators of light. Included are semiconductor QW's with band-to-band and intersubband transitions, graphene, two dimensional materials like MoS2 and polymers. The efficiency enhancement using either micro resonators or plasmonic structures is considered as well. The results indicate that the performance of different modulators depends on the very few characteristics of modulator, essentially on the ratio of absorption cross-section of the modulating medium to the waveguide cross-section and none of the currently fashionable 2D materials offer any meaningful improvement over a simple QW modulator. We also show that electro-optic modulators typically offer lower switching energies than all-optical modulators, but still their performance simply cannot match electronic devices.
Biography: Jacob B Khurgin has been a Professor of Electrical and Computer Engineering at Johns Hopkins University since he remembers himself, or, more precisely, since 1988. Prior to that he vaguely recalls being a Senior Member of Research Staff at Philips NV where he developed various useful things such as small kitchen appliances, lighting fixtures, display components and systems including 3-D projection TV. Satiated by things useful, Prof. Khurgin had decamped industry for academia to immerse himself into topics of dubious utility yet higher entertainment value. Prof. Khurgin's main area of expertise is difficult to pinpoint as it falls into the gap between optics and solid state electronics. In his 28 years at JHU Prof. Khurgin had made contributions of various degrees of relevance and importance in the fields of nonlinear optics, semiconductor optoelectronic devices, quantum-cascade lasers, optical communications, THz technology, microwave photonics, slow light, plasmonics, laser cooling, opto-mechanics, condensed matter physics, and to other fields that he can no longer recall. Prof Khurgin had authored over 320 technical papers, 500 Conference presentations, 5 book chapters, and 35 patents. More importantly, he is very fond of dogs and bicycles and he is also a Fellow of American Physical Society and Optical Society of America. Prof. Khurgin holds PhD from Polytechnic University of New York (Now elevated to the status of NYU school of Engineering).
Host: Alan Willner, x04664, willner@usc.edu
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Gerrielyn Ramos
-
ISE 651-Epstein Institute Seminar Speaker Series
Tue, Aug 30, 2016 @ 03:30 PM - 04:50 PM
Daniel J. Epstein Department of Industrial and Systems Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Sunderesh S. Heragu, Professor and Head Chair
Talk Title: Deterministic & Stochastic Models for Manufacuturing, Warehousing & Health Care Systems
Host: Dr. Julie Higle
Location: Ethel Percy Andrus Gerontology Center (GER) - 206
Audiences: Everyone Is Invited
Contact: Angela Reneau
-
Microsoft Info Session
Tue, Aug 30, 2016 @ 06:30 PM - 08:00 PM
Viterbi School of Engineering Career Connections
Workshops & Infosessions
Meet the company presentation!
Location: Seeley G. Mudd Building (SGM) - 101
Audiences: All Viterbi
Contact: RTH 218 Viterbi Career Connections
