Seminar

Engineering HDR Seminar Series 1&2_2011: (i) Fast and Accurate Human Detection for Video Applications using Edgelets; (ii) Complex Feature Alternating Decision Tree

(i) Mr Mohammed Shahnewaz Chowdhury; (ii)Mr Sok Hong Kuan, both are PSCT's postgraduate students


Date: 2011-04-26
Time: 14:00 to 15:30
Venue: Classroom 9-3-03


Abstract

(i) Fast and Accurate Human Detection for Video Applications using Edgelets

In automated video analysis, the performance of the detection stage is integral to the performance of subsequent stages such as tracking and behavior recognition. This talk described a method to boost the speed and accuracy of Wu and Nevatia’s edgelet based detectors  by incorporating motion information to isolate active regions before actually performing detection. Experimental results show that the detection is significantly improved by using this method.

(ii) Complex Feature Alternating Decision Tree

Complex number features are ubiquitous in many engineering and scientific applications. Many traditional classification algorithms including alternating decision tree are very powerful but not capable of handling complex domain data. Alternating decision tree is classifier that is intrinsically support boosting, hence inherent all desirable statistical properties of boosting methodology. This talk introduces base learners that enable application of alternating decision tree algorithm to complex domain data and describe how the base learners enhance performance of alternating decision trees on complex domain features.

About the Speaker

(i) Mohammed Shahnewaz Chowdhury received his BEng (Hons) degree with first class honors in Electrical and Computer Systems engineering from Monash University, Malaysia in 2009. He is currently pursuing his MEngSc (Research) with Monash University in a joint collaboration with ELID Sdn. Bhd. His main research areas include human detection, tracking and signal processing.

 (ii) Sok Hong Kuan received his BEng (Hons) degree with first class honors in Electrical and Computer Systems engineering from Monash University, Malaysia in 2010. He is currently pursuing his MEngSc (Research) with Monash University. His main research areas include embedded systems, machine learning, classification and statistical approximation.