Ramakrishna Vedantham

Mobile Visual Search

Mobile phones have evolved into powerful image and video processing devices equipped with high-resolution cameras, color displays, and hardware-accelerated graphics. They are also increasingly equipped with a global positioning system and connected to broadband wireless networks. All this enables a new class of applications that use the camera phone to initiate search queries about objects in visual proximity to the user (Figure 1). Such applications can be used, e.g., for identifying products, comparison shopping, finding information about movies, compact disks (CDs), real estate, print media, or artworks.

City-scale landmark identification on mobile devices

With recent advances in mobile computing, the demand for visual localization or landmark identification on mobile devices is gaining interest. We advance the state of the art in this area by fusing two popular representations of street-level image data — facade-aligned and viewpoint-aligned — and show that they contain complementary information that can be exploited to significantly improve the recall rates on the city scale. We also improve feature detection in low contrast parts of the street-level data, and discuss how to incorporate priors on a users position (e.g. given by noisy GPS readings or network cells), which previous approaches often ignore. Finally, and maybe most importantly, we present our results according to a carefully designed, repeatable evaluation scheme and make publicly available a set of 1.7 million images with ground truth labels, geotags, and calibration data, as well as a difficult set of cell phone query images. We provide these resources as a benchmark to facilitate further research in the area.

Landmark-based pedestrian navigation from collections of geotagged photos

Mobile phones are an attractive platform for landmark-based pedestrian navigation systems. To be practical, such a system must be able to automatically generate lightweight directions that can be displayed on these mobile devices. We present a system that leverages an online collection of geotagged photographs to automatically generate navigational instructions. These are presented to the user as a sequence of images of landmarks augmented with directional instructions. Both the landmark selection and image augmentation are done automatically. We present a user study that indicates these generated directions are beneficial to users and suggest areas for future improvement.

Residual enhanced visual vector as a compact signature for mobile visual search

Many mobile visual search (MVS) systems transmit query data from a mobile device to a remote server and search a database hosted on the server. In this paper, we present a new architecture for searching a large database directly on a mobile device, which can provide numerous benefits for network-independent, low-latency, and privacy-protected image retrieval. A key challenge for on-device retrieval is storing a large database in the limited RAM of a mobile device. To address this challenge, we develop a new compact, discriminative image signature called the Residual Enhanced Visual Vector (REVV) that is optimized for sets of local features which are fast to extract on mobile devices. REVV outperforms existing compact database constructions in the MVS setting and attains similar retrieval accuracy in large-scale retrieval as a Vocabulary Tree that uses 25x more memory. We have utilized REVV to design and construct a mobile augmented reality system for accurate, large-scale landmark recognition. Fast on-device search with REVV enables our system to achieve latencies around 1s per query regardless of external network conditions. The compactness of REVV allows it to also function well as a low-bitrate signature that can be transmitted to or from a remote server for an efficient expansion of the local database search when required.

Mobile product recognition

We present a mobile product recognition system for the camera-phone. By snapping a picture of a product with a camera-phone, the user can retrieve online information of the product. The product is recognized by an image-based retrieval system located on a remote server. Our database currently comprises more than one million entries, primarily products packaged in rigid boxes with printed labels, such as CDs, DVDs, and books. We extract low bit-rate descriptors from the query image and compress the location of the descriptors using location histogram coding on the camera-phone. We transmit the compressed query features, instead of a query image, to reduce the transmission delay. We use inverted index compression and fast geometric re-ranking on our database to provide a low delay image recognition response for large scale databases. Experimental timing results on different parts of the mobile product recognition system is reported in this work.

Fast geometric re-ranking for image-based retrieval

We present a fast and efficient geometric re-ranking method that can be incorporated in a feature based image-based retrieval system that utilizes a Vocabulary Tree (VT). We form feature pairs by comparing descriptor classification paths in the VT and calculate geometric similarity score of these pairs. We propose a location geometric similarity scoring method that is invariant to rotation, scale, and translation, and can be easily incorporated in mobile visual search and augmented reality systems. We compare the performance of the location geometric scoring scheme to orientation and scale geometric scoring schemes. We show in our experiments that re-ranking schemes can substantially improve recognition accuracy. We can also reduce the worst case server latency up to 1 sec and still improve the recognition performance.

Landmark-Based Pedestrian Navigation with Enhanced Spatial Reasoning

Computer vision techniques can enhance landmark-based navigation by better utilizing online photo collections. We use spatial reasoning to compute camera poses, which are then registered to the world using GPS information extracted from the image tags. Computed camera pose is used to augment the images with navigational arrows that fit the environment. We develop a system to use high-level reasoning to influence the selection of landmarks along a navigation path, and lower-level reasoning to select appropriate images of those landmarks. We also utilize an image matching pipeline based on robust local descriptors to give users of the system the ability to capture an image and receive navigational instructions overlaid on their current context. These enhancements to our previous navigation system produce a more natural navigation plan and more understandable images in a fully automatic way.

Inverted Index Compression for Scalable Image Matching

To perform fast image matching against large databases, a Vocabulary Tree (VT) uses an inverted index that maps from each tree node to database images which have visited that node. The inverted index can require gigabytes of memory, which significantly slows down the database server. In this paper, we design, develop, and compare techniques for inverted index compression for image-based retrieval. We show that these techniques significantly reduce memory usage, by as much as 5x, without loss in recognition accuracy. Our work includes fast decoding methods, an offline database reordering scheme that exploits the similarity between images for additional memory savings, and a generalized coding scheme for soft-binned feature descriptor histograms. We also show that reduced index memory permits memory-intensive image matching techniques that boost recognition accuracy.

Streaming mobile augmented reality on mobile phones

Continuous recognition and tracking of objects in live video captured on a mobile device enables real-time user interaction. We demonstrate a streaming mobile augmented reality system with 1 second latency. User interest is automatically inferred from camera movements, so the user never has to press a button. Our system is used to identify and track book and CD covers in real time on a phones viewfinder. Efficient motion estimation is performed at 30 frames per second on a phone, while fast search through a database of 20,000 images is performed on a server.

Low latency image retrieval with progressive transmission of CHoG descriptors

To reduce network latency for mobile visual search, we propose schemes for progressive transmission of Compressed Histogram of Gradients (CHoG) descriptors. Progressive transmission reduces the amount of transmitted data and enables early termination on the server, thus reducing end-to-end system latency. With progressive transmission of CHoG descriptors, we are able to reduce network latency to ~1 second in a 3G network. We report a 4× decrease in end-to-end system latency compared to transmitting uncompressed SIFT descriptors or JPEG images.