Mohamed Aly

Real time detection of lane markers in urban streets

We present a robust and real time approach to lane marker detection in urban streets. It is based on generating a top view of the road, filtering using selective oriented Gaussian filters, using RANSAC line fitting to give initial guesses to a new and fast RANSAC algorithm for fitting Bezier Splines, which is then followed by a post-processing step. Our algorithm can detect all lanes in still images of the street in various conditions, while operating at a rate of 50 Hz and achieving comparable results to previous techniques.

Indexing in large scale image collections: Scaling properties and benchmark

Indexing quickly and accurately in a large collection of images has become an important problem with many applications. Given a query image, the goal is to retrieve matching images in the collection. We compare the structure and properties of seven different methods based on the two leading approaches: voting from matching of local descriptors vs. matching histograms of visual words, including some new methods. We derive theoretical estimates of how the memory and computational cost scale with the number of images in the database. We evaluate these properties empirically on four real-world datasets with different statistics. We discuss the pros and cons of the different methods and suggest promising directions for future research.

Scaling object recognition: Benchmark of current state of the art techniques

Scaling from hundreds to millions of objects is the next challenge in visual recognition. We investigate and benchmark the scalability properties (memory requirements, runtime, recognition performance) of the state-of-the-art object recognition techniques: the forest of k-d trees, the locality sensitive hashing (LSH) method, and the approximate clustering procedure with the tf-idf inverted index. The characterization of the images was performed with SIFT features. We conduct experiments on two new datasets of more than 100,000 images each, and quantify the performance using artificial and natural deformations. We analyze the results and point out the pitfalls of each of the compared methodologies suggesting potential new research avenues for the field.

Automatic discovery of image families: Global vs. local features

Gathering a large collection of images has been made quite easy by social and image sharing websites, e.g. flickr.com. However, using such collections faces the problem that they contain a large number of duplicates and highly similar images. This work tackles the problem of how to automatically organize image collections into sets of similar images, called image families hereinafter. We thoroughly compare the performance of two approaches to measure image similarity: global descriptors vs. a set of local descriptors. We assess the performance of these approaches as the problem scales up to thousands of images and hundreds of families. We present our results on a new dataset of CD/DVD game covers.

Towards automated large scale discovery of image families

Gathering large collections of images is quite easy nowadays with the advent of image sharing Web sites, such as flickr.com. However, such collections inevitably contain duplicates and highly similar images, what we refer to as image families. Automatic discovery and cataloguing of such similar images in large collections is important for many applications, e.g. image search, image collection visualization, and research purposes among others. In this work, we investigate this problem by thoroughly comparing two broad approaches for measuring image similarity: global vs. local features. We assess their performance as the image collection scales up to over 11,000 images with over 6,300 families. We present our results on three datasets with different statistics, including two new challenging datasets. Moreover, we present a new algorithm to automatically determine the number of families in the collection with promising results.

CompactKdt: Compact signatures for accurate large scale object recognition

We present a novel algorithm, Compact Kd-Trees (CompactKdt), that achieves state-of-the-art performance in searching large scale object image collections. The algorithm uses an order of magnitude less storage and computations by making use of both the full local features (e.g. SIFT) and their compact binary signatures to build and search the K-Tree. We compare classical PCA dimensionality reduction to three methods for generating compact binary representations for the features: Spectral Hashing, Locality Sensitive Hashing, and Locality Sensitive Binary Codes. CompactKdt achieves significant performance gain over using the binary signatures alone, and comparable performance to using the full features alone. Finally, our experiments show significantly better performance than the state-of-the-art Bag of Words (BoW) methods with equivalent or less storage and computational cost.

Online learning for parameter selection in large scale image search

We explore using online learning for selecting the best parameters of Bag of Words systems when searching large scale image collections. We study two algorithms for no regret online learning: Hedge algorithm that works in the full information setting, and Exp3 that works in the bandit setting. We use these algorithms for parameter selection in two scenarios: (a) using a training set to obtain weights for the different parameters, then either choosing the parameter setting with maximum weight or combining their results with weighted majority vote; (b) working fully online by selecting a parameter combination at every time step. We demonstrate the usefulness of online learning using experiments on four different real world datasets.