This paper introduces a novel perception framework that has the ability to identify and track objects in autonomous vehicle's field of view. The proposed algorithms don't require any training for achieving this goal. The framework makes use of ego-vehicle's pose estimation and a KD-Tree-based segmentation algorithm to generate object clusters. In turn, using a VFH technique, the geometry of each identified object cluster is translated into a multi-modal PDF and a motion model is initiated with every new object cluster for the purpose of robust spatio-temporal tracking. The methodology further uses statistical properties of high-dimensional probability density functions and Bayesian motion model estimates to identify and track objects from frame to frame. The effectiveness of the methodology is tested on a KITTI dataset. The results show that the median tracking accuracy is around 91% with an end-to-end computational time of 153 milliseconds
We propose a new approach for combining deep-learned non-metric monocular depth with affine correspondences (ACs) to estimate the relative pose of two calibrated cameras from a single correspondence. Considering the depth information and affine features, two new constraints on the camera pose are derived. The proposed solver is usable within 1-point RANSAC approaches. Thus, the processing time of the robust estimation is linear in the number of correspondences and, therefore, orders of magnitude faster than by using traditional approaches. The proposed 1AC+D solver is tested both on synthetic data and on 110395 publicly available real image pairs where we used an off-the-shelf monocular depth network to provide up-to-scale depth per pixel. The proposed 1AC+D leads to similar accuracy as traditional approaches while being significantly faster. When solving large-scale problems, e.g., pose-graph initialization for Structure-from-Motion (SfM) pipelines, the overhead of obtaining ACs and monocular depth is negligible compared to the speed-up gained in the pairwise geometric verification, i.e., relative pose estimation. This is demonstrated on scenes from the 1DSfM dataset using a state-of-the-art global SfM algorithm. Source code: https://github.com/eivan/one-ac-pose
We give the first efficient algorithm for the problem of list-decodable subspace recovery. Our algorithm takes input $n$ samples $\alpha n$ ($\alpha\ll 1/2$) are generated i.i.d. from Gaussian distribution $\mathcal{N}(0,\Sigma_*)$ on $\mathbb{R}^d$ with covariance $\Sigma_*$ of rank $r$ and the rest are arbitrary, potentially adversarial outliers. It outputs a list of $O(1/\alpha)$ projection matrices guaranteed to contain a projection matrix $\Pi$ such that $\|\Pi-\Pi_*\|_F^2 = \kappa^4 \log (r) \tilde{O}(1/\alpha^2)$, where $\tilde{O}$ hides polylogarithmic factors in $1/\alpha$. Here, $\Pi_*$ is the projection matrix to the range space of $\Sigma_*$. The algorithm needs $n=d^{\log (r \kappa) \tilde{O}(1/\alpha^2)}$ samples and runs in time $n^{\log (r \kappa) \tilde{O}(1/\alpha^4)}$ time where $\kappa$ is the ratio of the largest to smallest non-zero eigenvalues of $\Sigma_*$. Our algorithm builds on the recently developed framework for list-decodable learning via the sum-of-squares (SoS) method [KKK'19, RY'20] with some key technical and conceptual advancements. Our key conceptual contribution involves showing a (SoS "certified") lower bound on the eigenvalues of covariances of arbitrary small subsamples of an i.i.d. sample of a certifiably anti-concentrated distribution. One of our key technical contributions gives a new method that allows error reduction "within SoS" with only a logarithmic cost in the exponent in the running time (in contrast to polynomial cost in [KKK'19, RY'20]. In a concurrent and independent work, Raghavendra and Yau proved related results for list-decodable subspace recovery [RY'20].
In this paper, we address the problem of automatic three-dimensional cephalometric analysis. Cephalometric analysis performed on lateral radiographs doesn't fully exploit the structure of 3D objects due to projection onto the lateral plane. With the development of three-dimensional imaging techniques such as CT, several analysis methods have been proposed that extend to the 3D case. The analysis based on these methods is invariant to rotations and translations and can describe difficult skull deformation, where 2D cephalometry has no use. In this paper, we provide a wide overview of existing approaches for cephalometric landmark regression. Moreover, we perform a series of experiments with state of the art 3D convolutional neural network (CNN) based methods for keypoint regression: direct regression with CNN, heatmap regression and Softargmax regression. For the first time, we extensively evaluate the described methods and demonstrate their effectiveness in the estimation of Frankfort Horizontal and cephalometric points locations for patients with severe skull deformations. We demonstrate that Heatmap and Softargmax regression models provide sufficient regression error for medical applications (less than 4 mm). Moreover, the Softargmax model achieves 1.15o inclination error for the Frankfort horizontal. For the fair comparison with the prior art, we also report results projected on the lateral plane.
The presence of bacteria or fungi in the bloodstream of patients is abnormal and can lead to life-threatening conditions. A computational model based on a bidirectional long short-term memory artificial neural network, is explored to assist doctors in the intensive care unit to predict whether examination of blood cultures of patients will return positive. As input it uses nine monitored clinical parameters, presented as time series data, collected from 2177 ICU admissions at the Ghent University Hospital. Our main goal is to determine if general machine learning methods and more specific, temporal models, can be used to create an early detection system. This preliminary research obtains an area of 71.95% under the precision recall curve, proving the potential of temporal neural networks in this context.
Local features e.g. SIFT and its affine and learned variants provide region-to-region rather than point-to-point correspondences. This has recently been exploited to create new minimal solvers for classical problems such as homography, essential and fundamental matrix estimation. The main advantage of such solvers is that their sample size is smaller, e.g., only two instead of four matches are required to estimate a homography. Works proposing such solvers often claim a significant improvement in run-time thanks to fewer RANSAC iterations. We show that this argument is not valid in practice if the solvers are used naively. To overcome this, we propose guidelines for effective use of region-to-region matches in the course of a full model estimation pipeline. We propose a method for refining the local feature geometries by symmetric intensity-based matching, combine uncertainty propagation inside RANSAC with preemptive model verification, show a general scheme for computing uncertainty of minimal solvers results, and adapt the sample cheirality check for homography estimation. Our experiments show that affine solvers can achieve accuracy comparable to point-based solvers at faster run-times when following our guidelines. We make code available at https://github.com/danini/affine-correspondences-for-camera-geometry.
We present a framework for interactive design of new image stylizations using a wide range of predefined filter blocks. Both novel and off-the-shelf image filtering and rendering techniques are extended and combined to allow the user to unleash their creativity to intuitively invent, modify, and tune new styles from a given set of filters. In parallel to this manual design, we propose a novel procedural approach that automatically assembles sequences of filters, leading to unique and novel styles. An important aim of our framework is to allow for interactive exploration and design, as well as to enable videos and camera streams to be stylized on the fly. In order to achieve this real-time performance, we use the \textit{Best Linear Adaptive Enhancement} (BLADE) framework -- an interpretable shallow machine learning method that simulates complex filter blocks in real time. Our representative results include over a dozen styles designed using our interactive tool, a set of styles created procedurally, and new filters trained with our BLADE approach.
The video game industry has adopted recommendation systems to boost users interest with a focus on game sales. Other exciting applications within video games are those that help the player make decisions that would maximize their playing experience, which is a desirable feature in real-time strategy video games such as Multiplayer Online Battle Arena (MOBA) like as DotA and LoL. Among these tasks, the recommendation of items is challenging, given both the contextual nature of the game and how it exposes the dependence on the formation of each team. Existing works on this topic do not take advantage of all the available contextual match data and dismiss potentially valuable information. To address this problem we develop TTIR, a contextual recommender model derived from the Transformer neural architecture that suggests a set of items to every team member, based on the contexts of teams and roles that describe the match. TTIR outperforms several approaches and provides interpretable recommendations through visualization of attention weights. Our evaluation indicates that both the Transformer architecture and the contextual information are essential to get the best results for this item recommendation task. Furthermore, a preliminary user survey indicates the usefulness of attention weights for explaining recommendations as well as ideas for future work. The code and dataset are available at: https://github.com/ojedaf/IC-TIR-Lol.
Learning graph generative models is a challenging task for deep learning and has wide applicability to a range of domains like chemistry, biology and social science. However current deep neural methods suffer from limited scalability: for a graph with $n$ nodes and $m$ edges, existing deep neural methods require $\Omega(n^2)$ complexity by building up the adjacency matrix. On the other hand, many real world graphs are actually sparse in the sense that $m\ll n^2$. Based on this, we develop a novel autoregressive model, named BiGG, that utilizes this sparsity to avoid generating the full adjacency matrix, and importantly reduces the graph generation time complexity to $O((n + m)\log n)$. Furthermore, during training this autoregressive model can be parallelized with $O(\log n)$ synchronization stages, which makes it much more efficient than other autoregressive models that require $\Omega(n)$. Experiments on several benchmarks show that the proposed approach not only scales to orders of magnitude larger graphs than previously possible with deep autoregressive graph generative models, but also yields better graph generation quality.
Machine learning models differ in terms of accuracy, computational/memory complexity, training time, and adaptability among other characteristics. For example, neural networks (NNs) are well-known for their high accuracy due to the quality of their automatic feature extraction while brain-inspired hyperdimensional (HD) learning models are famous for their quick training, computational efficiency, and adaptability. This work presents a hybrid, synergic machine learning model that excels at all the said characteristics and is suitable for incremental, on-line learning on a chip. The proposed model comprises an NN and a classifier. The NN acts as a feature extractor and is specifically trained to work well with the classifier that employs the HD computing framework. This work also presents a parameterized hardware implementation of the said feature extraction and classification components while introducing a compiler that maps any arbitrary NN and/or classifier to the aforementioned hardware. The proposed hybrid machine learning model has the same level of accuracy (i.e. 1%) as NNs while achieving at least 10% improvement in accuracy compared to HD learning models. Additionally, the end-to-end hardware realization of the hybrid model improves power efficiency by 1.60x compared to state-of-the-art, high-performance HD learning implementations while improving latency by 2.13x. These results have profound implications for the application of such synergic models in challenging cognitive tasks.