Differences

This shows you the differences between two versions of the page.

--- ece4580:module_detection [2017/01/24 05:02] – [Object Detection] typos
+++ ece4580:module_detection [2024/08/20 21:38] (current) – external edit 127.0.0.1
@@ Line 1: / Line 1: @@
-====== Object Recognition ======
+====== Object Detection ======
+**Note:** To be filled out on Friday or Saturday.
+  - Boosting
+  - Sliding window
 /*
@@ Line 7: / Line 11: @@
 */
+===== Module #1: Human Detection =====
+The classic human detection paper is by Dalal and Triggs, and it involves using the Histogram of Oriented Gradients (HOG) feature descriptor together with Support Vector Machines.  It does quite well, though more modern and more expensive methods have superceded it.
-===== Module #1 =====
-Clustering
-  - Study [[https://sites.google.com/site/dataclusteringalgorithms/k-means-clustering-algorithm|k-means clustering algorithm]] and the algorithmic steps for k-means clustering.
-  - Download (or clone) the clustering skeleton code [[https://github.gatech.edu/fchu9/ECE4580_LearningModules/tree/master/objectRecognition/clustering|here]]
-  - Implement k-means clustering algorithm working in RGB space by following the algorithmic steps. You are welcome to implement from scratch without skeleton code.
-  - Test your algorithm on segmenting the image //segmentation.jpg// using k=3
-  - Try different random initialization and show corresponding results.
-  - Comment on your different segmentation results.
------------------
-===== Module #2 =====
-Object Recognition
-  - Study the [[https://www.youtube.com/watch?v=unCLMMsZAh8|bag-of-words]] approach for classification/Recognition task
-  - We begin with implementing a simple but powerful recognition system to classify //faces// and //cars//.
-  - Check [[https://github.gatech.edu/fchu9/ECE4580_LearningModules/tree/master/objectRecognition/simpleBoW|here]] for skeleton code. First, follow the README to setup the dataset and vlfeat library.
-  - In our implementation, you will find [[http://www.vlfeat.org/index.html|vlfeat library]] very useful. One may use vl_sift, vl_kmeans and vl_kdtreebuild.
-  - Now, use first 40 images in both categories for training.
-  - Extract SIFT features from each image
-  - Derive k codewords with k-means clustering in module 1.
-  - Compute histogram of codewords using [[https://en.wikipedia.org/wiki/K-d_tree|kd-tree algorithm]] using vlfeat.
-  - Use the rest of 50 images in both categories to test your implementation.
------------------
+===== Module #2: Boosting =====
+Boosting as a concept is about creating a very accurate detector from a series of somewhat low accuracy detectors.  The trick is to control the false positive rate (have it be very low) while tolerating false negatives.  Cascading enough of these together will eventually create a detector that has bot a low false positive rate and a low false negative rate (after all, how many times can one be wrong in a row?).
+----------
 ;#;
 [[ECE4580:Modules|ECE4580 Learning Modules]]
 ;#;