Accurate lane detection is critical for navigation in autonomous vehicles, particularly the active lane which demarcates the single road space that the vehicle is currently traveling on. Recent state-of-the-art lane detection algorithms utilize convolutional neural networks (CNNs) to train deep learning models on popular benchmarks such as TuSimple and CULane. While each of these models works particularly well on train and test inputs obtained from the same dataset, the performance drops significantly on unseen datasets of different environments. In this paper, we present a real-time robust neural network output enhancement for active lane detection (RONELD) method to identify, track, and optimize active lanes from deep learning probability map outputs. We first adaptively extract lane points from the probability map outputs, followed by detecting curved and straight lanes before using weighted least squares linear regression on straight lanes to fix broken lane edges resulting from fragmentation of edge maps in real images. Lastly, we hypothesize true active lanes through tracking preceding frames. Experimental results demonstrate an up to two-fold increase in accuracy using RONELD on cross-dataset validation tests.

This paper presents a novel feature-based method that is built upon a convolutional neural network (CNN) to learn the deep representation for multimodal retinal image registration. We coined the algorithm deep step patterns, in short DeepSPa. Most existing deep learning based methods require a set of manually labeled training data with known corresponding spatial transformations, which limits the size of training datasets. By contrast, our method is fully automatic and scale well to different image modalities with no human intervention. We generate feature classes from simple step patterns within patches of connecting edges formed by vascular junctions in multiple retinal imaging modalities. We leverage CNN to learn and optimize the input patches to be used for image registration. Spatial transformations are estimated based on the output possibility of the fully connected layer of CNN for a pair of images. One of the key advantages of the proposed algorithm is its robustness to non-linear intensity changes, which widely exist on retinal images due to the difference of acquisition modalities. We validate our algorithm on extensive challenging datasets comprising poor quality multimodal retinal images which are adversely affected by pathologies (diseases), speckle noise and low resolutions. The experimental results demonstrate the robustness and accuracy over state-of-the-art multimodal image registration algorithms.

This paper presents a technique for real-time texture-less object recognition and tracking on mobile devices. Our proposed algorithm is an even lighter-weight version of the recent state-of-the-art binary-based texture-less object detector BIND (Binary Integrated Net Descriptor), primarily customized for mobile device applications. This modification, termed BIND-Lite, employs various techniques to overcome the low-computational power of current mobile devices, while mostly retaining the texture-less object detection robustness of the original BIND. On current generation mobile devices, BIND-Lite was able to achieve runtime rates of up to 30 frames per second. To evaluate our algorithm, we have also designed a mobile augmented reality application coined IMPRINT, which renders logos/images onto detected objects to showcase BIND-Lite in a real-time mobile augmented reality setting.

This paper presents BIND (Binary Integrated Net Descriptor), a texture-less object detector that encodes multi-layered binary-represented nets for high precision edge-based description. Our proposed concept aligns layers of object-sized patches (nets) onto highly fragmented occlusion resistant line-segment midpoints (linelets) to encode regional information into efficient binary strings. These lightweight nets encourage discriminative object description through their high-spatial resolution, enabling highly precise encoding of the objects edges and internal texture-less information. BIND achieved various invariant properties such as rotation, scale and edge-polarity through its unique binary logical-operated encoding and matching techniques, while performing remarkably well in occlusion and clutter. Apart from yielding efficient computational performance, BIND also attained remarkable recognition rates surpassing recent state-of-the-art texture-less object detectors such as BORDER, BOLD and LINE2D.

This paper presents an algorithm coined BORDER (Bounding Oriented-Rectangle Descriptors for Enclosed Regions) for texture-less object recognition. By fusing a regional object encompassment concept with descriptor-based pipelines, we extend local-patches into scalable object-sized oriented rectangles for optimal object information encapsulation with minimal outliers. We correspondingly introduce a modified line-segment detection technique termed Linelets to stabilize keypoint repeatability in homogenous conditions. In addition, a unique sampling technique facilitates the incorporation of robust angle primitives to produce discriminative rotation-invariant descriptors. BORDER's high competence in object recognition particularly excels in homogenous conditions obtaining superior detection rates in the presence of high-clutter, occlusion and scale-rotation changes when compared with modern state-of-the-art texture-less object detectors such as BOLD and LINE2D on public texture-less object databases.

Existing feature descriptor-based methods on retinal image registration are mainly based on scale-invariant feature transform (SIFT) or partial intensity invariant feature descriptor (PIIFD). While these descriptors are often being exploited, they do not work very well upon unhealthy multimodal images with severe diseases. Additionally, the descriptors demand high dimensionality to adequately represent the features of interest. The higher the dimensionality, the greater the consumption of resources (e.g. memory space). To this end, this paper introduces a novel registration algorithm coined low-dimensional step pattern analysis (LoSPA), tailored to achieve low dimensionality while providing sufficient distinctiveness to effectively align unhealthy multimodal image pairs. The algorithm locates hypotheses of robust corner features based on connecting edges from the edge maps, mainly formed by vascular junctions. This method is insensitive to intensity changes, and produces uniformly distributed features and high repeatability across the image domain. The algorithm continues with describing the corner features in a rotation invariant manner using step patterns. These customized step patterns are robust to non-linear intensity changes, which are well-suited for multimodal retinal image registration. Apart from its low dimensionality, the LoSPA algorithm achieves about two-fold higher success rate in multimodal registration on the dataset of severe retinal diseases when compared to the top score among state-of-the-art algorithms.

We describe the prototype of an image retrieval system used for mobile guide applications. It allows users to send image queries of urban scenes using camera phones. The system uses a database of views of scenes to determine the poses of query views provided by the users. Information is then mapped onto the query views. Our approach is based on a fully affine invariant descriptor, coined PRIUS, which can identify corresponding building facades across widely separated views despite the highly repetitive nature of the man-made environments. The system is substantiated by experiments that show that our approach outperforms the state-of-the-art approaches such as SIFT (scale-invariant feature transform) and MSER (maximally stable external regions) in image retrieval. © 2012 Wiley Periodicals, Inc.

In the literature, we have seen a boom in wide-baseline matching approaches proposed for locating correspondences between images. However, wrong correspondences or the so-called outliers are still rather inevitable, especially in urban environments with the presence of repetitive structures, and/or a large dissimilarity in viewpoints. In this paper, we propose a verification model to optimize the image matching results by significantly reducing the number of outliers. Several geometric and appearance-based measurements are exploited, and conditional probability is used to compute the probability of each true correspondence. The model is validated by extensive experiments on images from the ZuBud database, which are taken in different weather conditions, seasons, and with different cameras. It is also demonstrated on a real-time application of an image-based navigation system. © 2010 Wiley Periodicals, Inc.

This paper presents a novel approach to finding point correspondences between images of building facades with wide viewpoint variations, and at the same time returning a large list of true matches between the images. Such images comprise repetitive and symmetric patterns, which render popular algorithms e.g., SIFT to be ineffective. Feature descriptors such as SIFT that are based on region patches are also unstable under large viewing angle variations. In this paper, we integrate both the appearance and geometric properties of an image to find unique matches. First we extract hypotheses of building facades based on a robust line fitting algorithm. Each hypothesis is defined by a planar convex quadrilateral in the image, which we call a “q-region”, and the four corners of each q-region provide the inputs from which a projective transformation model is derived. Next, a set of interest points are extracted from the images and are used to evaluate the correctness of the transformation model. The transformation model with the largest set of matched interest points is selected as the correct model, and this model also returns the best pair of corresponding q-regions and the most number of point correspondences in the two images. Extensive experimental results demonstrate the robustness of our approach in which we achieve a tenfold increase in true matches when compared to state of the art techniques such as SIFT and MSER.

Our paper presents a system for efficient recognition of landmarks taken from camera phones. Information such as tutorial rooms within the captured landmarks is returned to user within seconds. The system uses a database of multiple viewpoint's images for matching. Various navigational aids and sensors are used to optimize accuracy and retrieval time by providing complementary information about relative position and viewpoint of each query image. This makes our system less sensitive to orientation, scale and perspective distortion. Multi-scale approach and a reliability score model are proposed in this application. Our system is validated by several experiments in the campus, with images taken from different resolution's camera phones, positions and times of day.