RGB-based pedestrian detection is a challenging task in low light and adverse weather conditions because image quality can degrade rather significantly. Including other modalities such as thermal and gated imaging sensors can, on the other hand, significantly improve the detection performance in these conditions. However, these sensors are expensive, and including them may cause design and manufacturing challenges. In this paper, we propose a new framework that utilizes Cross Modality Knowledge Distillation (CMKD) to improve the performance of RGB-only pedestrian detection in low light and adverse weather conditions. Specifically, we develop two CMKD methods that rely on feature-based knowledge distillation and adversarial training to transfer knowledge from a pedestrian detector (teacher) that is trained using multiple modalities to a single modality detector (student) that is trained using RGB images only. Experimental results using the "Seeing Through Fog" dataset show that both of our proposed methods outperform the baseline detector in terms of detection accuracy without increasing computational complexity during inference. In particular, the proposed methods reduce the performance gap between teacher and baseline models by up to 55%.

The performance of the current collision avoidance systems in Autonomous Vehicles (AV) and Advanced Driver Assistance Systems (ADAS) can be drastically affected by low light and adverse weather conditions. Collisions with large animals such as deer in low light cause significant cost and damage every year. In this paper, we propose the first AI-based method for future trajectory prediction of large animals and mitigating the risk of collision with them in low light. In order to minimize false collision warnings, in our multi-step framework, first, the large animal is accurately detected and a preliminary risk level is predicted for it and low-risk animals are discarded. In the next stage a multi-stream CONV-LSTM-based encoder-decoder framework is designed to predict the future trajectory of the potentially high-risk animals. The proposed model uses camera motion prediction as well as the local and global context of the scene to generate accurate predictions. Furthermore, this paper introduces a new dataset of FIR videos for large animal detection and risk estimation in real nighttime driving scenarios. Our experiments show promising results of the proposed framework in adverse conditions. Our code is available online1.

Abstract Recent work in computability theory has focused on various notions of asymptotic computability, which capture the idea of a set being “almost computable.” One potentially upsetting result is that all four notions of asymptotic computability admit “almost computable” sets in every Turing degree via coding tricks, contradicting the notion that “almost computable” sets should be computationally close to the computable sets. In response, Astor introduced the notion of intrinsic density: a set has defined intrinsic density if its image under any computable permutation has the same asymptotic density. Furthermore, introduced various notions of intrinsic computation in which the standard coding tricks cannot be used to embed intrinsically computable sets in every Turing degree. Our goal is to study the sets which are intrinsically small, i.e. those that have intrinsic density zero. We begin by studying which computable functions preserve intrinsic smallness. We also show that intrinsic smallness and hyperimmunity are computationally independent notions of smallness, i.e. any hyperimmune degree contains a Turing-equivalent hyperimmune set which is “as large as possible” and therefore not intrinsically small. Our discussion concludes by relativizing the notion of intrinsic smallness and discussing intrinsic computability as it relates to our study of intrinsic smallness.

Last-mile delivery systems commonly propose the use of autonomous robotic vehicles to increase scalability and efficiency. The economic inefficiency of collecting accurate prior maps for navigation motivates the use of planning algorithms that operate in unmapped environments. However, these algorithms typically waste time exploring regions that are unlikely to contain the delivery destination. Context is key information about structured environments that could guide exploration toward the unknown goal location, but the abstract idea is difficult to quantify for use in a planning algorithm. Some approaches specifically consider contextual relationships between objects, but would perform poorly in object-sparse environments like outdoors. Recent deep learning-based approaches consider context too generally, making training/transferability difficult. Therefore, this work proposes a novel formulation of utilizing context for planning as an image-to-image translation problem, which is shown to extract terrain context from semantic gridmaps, into a metric that an exploration-based planner can use. The proposed framework has the benefit of training on a static dataset instead of requiring a time-consuming simulator. Across 42 test houses with layouts from satellite images, the trained algorithm enables a robot to reach its goal 189% faster than with a context-unaware planner, and within 63% of the optimal path computed with a prior map. The proposed algorithm is also implemented on a vehicle with a forward-facing camera in a high-fidelity, Unreal simulation of neighborhood houses.

MOTIVATION: Orthologous gene identification is fundamental to all aspects of biology. For example, ortholog identification between species can provide functional insights for genes of unknown function and is a necessary step in phylogenetic inference. Currently, most ortholog identification algorithms require all-versus-all BLAST comparisons, which are time-consuming and memory intensive. RESULTS: In contrast to existing approaches, JustOrthologs exploits the conservation of gene structure by using the lengths of coding sequence regions and dinucleotide percentages to identify orthologs. In comparison to OrthoMCL, OMA and OrthoFinder, JustOrthologs decreases ortholog identification runtime by more than 96% and achieves comparable precision and recall scores. The computational speedup allowed us to conduct pairwise comparisons of 1197 complete genomes (780 eukaryotes and 417 archaea). We confirmed gene annotations for 384 120 genes, grouped 1 675 415 genes in previously unreported ortholog groups, and identified 51 429 potentially mislabeled genes across 622 843 ortholog groups. AVAILABILITY AND IMPLEMENTATION: JustOrthologs is an open source collaborative software package available in the GitHub repository: https://github.com/ridgelab/JustOrthologs/. All test FASTA files used for comparisons are freely available at https://github.com/ridgelab/JustOrthologs/comparisonFastaFiles/. Reference genomes used in this work are available for download from the NCBI repository: ftp://ftp.ncbi.nih.gov/genomes/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

This paper presents a robotic system implementation featuring an autonomy solution that incorporates human intents through effective human-robot interactions. More specifically, vision-based human pose estimation is used to identify gestures that correspond to human intents. These intents are mapped to predefined commands that schedule autonomous operations of the robotic system. The paper presents an overview of an autonomy solution for mobile robots, an approach to human-following operation, and an approach to automated decision-making for parking operations. Experimental results of the physical robot implementation are presented.

Autonomous Mobility On Demand (MOD) systems can utilize fleet management strategies in order to provide a high customer quality of service (QoS). Previous works on autonomous MOD systems have developed methods for rebalancing single capacity vehicles, where QoS is maintained through large fleet sizing. This work focuses on MOD systems utilizing a small number of vehicles, such as those found on a campus, where additional vehicles cannot be introduced as demand for rides increases. A predictive positioning method is presented for improving customer QoS by identifying key locations to position the fleet in order to minimize expected customer wait time. Ridesharing is introduced as a means for improving customer QoS as arrival rates increase. However, with ridesharing perceived QoS is dependent on an often unknown customer preference. To address this challenge, a customer ratings model, which learns customer preference from a 5-star rating, is developed and incorporated directly into a ridesharing algorithm. The predictive positioning and ridesharing methods are applied to simulation of a real-world campus MOD system. A combined predictive positioning and ridesharing approach is shown to reduce customer service times by up to 29%. and the customer ratings model is shown to provide the best overall MOD fleet management performance over a range of customer preferences.

In autonomous Mobility on Demand (MOD) systems, customers request rides from a fleet of shared vehicles that can be automatically positioned in response to customer demand. Recent approaches to MOD systems have focused on environments where customers can only request rides through an app or by waiting at a station. This paper develops MOD fleet management approaches for ride hailing, where customers may instead request rides simply by hailing a passing vehicle, an approach of particular importance for campus MOD systems. The challenge for ride hailing is that customer demand is not explicitly provided as it would be with an app, but rather customers are only served if a vehicle happens to be located at the arrival location. This work focuses on maximizing the number of served hailing customers in an MOD system by learning and utilizing customer demand. A Bayesian framework is used to define a novel customer demand model which incorporates observed pedestrian traffic to estimate customer arrival locations with a quantification of uncertainty. An exploration planner is proposed which routes MOD vehicles in order to reduce arrival rate uncertainty. A robust ride hailing fleet management planner is proposed which routes vehicles under the presence of uncertainty using a chance-constrained formulation. Simulation of a real-world MOD system on MIT's campus demonstrates the effectiveness of the planners. The customer demand model and exploration planner are demonstrated to reduce estimation error over time and the ride hailing planner is shown to improve the fraction of served customers in the system by 73% over a baseline exploration approach.

MOTIVATION: One of the main challenges with bioinformatics software is that the size and complexity of datasets necessitate trading speed for accuracy, or completeness. To combat this problem of computational complexity, a plethora of heuristic algorithms have arisen that report a 'good enough' solution to biological questions. However, in instances such as Simple Sequence Repeats (SSRs), a 'good enough' solution may not accurately portray results in population genetics, phylogenetics and forensics, which require accurate SSRs to calculate intra- and inter-species interactions. RESULTS: We present Kmer-SSR, which finds all SSRs faster than most heuristic SSR identification algorithms in a parallelized, easy-to-use manner. The exhaustive Kmer-SSR option has 100% precision and 100% recall and accurately identifies every SSR of any specified length. To identify more biologically pertinent SSRs, we also developed several filters that allow users to easily view a subset of SSRs based on user input. Kmer-SSR, coupled with the filter options, accurately and intuitively identifies SSRs quickly and in a more user-friendly manner than any other SSR identification algorithm. AVAILABILITY AND IMPLEMENTATION: The source code is freely available on GitHub at https://github.com/ridgelab/Kmer-SSR. CONTACT: [email protected].

Many robotic applications require repeated, on-demand motion planning in mapped environments. In addition, the presence of other dynamic agents, such as people, often induces frequent, dynamic changes in the environment. Having a potential function that encodes pairwise cost-to-go can be useful for improving the computational speed of finding feasible paths, and for guiding local searches around dynamic obstacles. However, since storing pairwise potential can be impractical given the O(|V|2) memory requirement, existing work often needs to compute a potential function for each query to a new goal, which would require a substantial online computation. This work addresses the problem by using diffusion maps, a machine learning algorithm, to learn the map's geometry and develop a memory-efficient parametrization (O(|V|)) of pairwise potentials. Specially, each state in the map is transformed to a diffusion coordinate, in which pairwise Euclidean distance is shown to be a meaningful similarity metric. We develop diffusion-based motion planning algorithms and, through extensive numerical evaluation, show that the proposed algorithms find feasible paths of similar quality with orders of magnitude improvement in computational speed compared with single-query methods. The proposed algorithms are implemented on hardware to enable real-time autonomous navigation in an indoor environment with frequent interactions with pedestrians.

Mobility On Demand (MOD) systems are revolutionizing transportation in urban settings by improving vehicle utilization and reducing parking congestion. A key factor in the success of an MOD system is the ability to measure and respond to real-time customer arrival data. Real time traffic arrival rate data is traditionally difficult to obtain due to the need to install fixed sensors throughout the MOD network. This paper presents a framework for measuring pedestrian traffic arrival rates using sensors onboard the vehicles that make up the MOD fleet. A novel distributed fusion algorithm is presented which combines onboard LIDAR and camera sensor measurements to detect trajectories of pedestrians with a 90% detection hit rate with 1.5 false positives per minute. A novel moving observer method is introduced to estimate pedestrian arrival rates from pedestrian trajectories collected from mobile sensors. The moving observer method is evaluated in both simulation and hardware and is shown to achieve arrival rate estimates comparable to those that would be obtained with multiple stationary sensors.

BACKGROUND: Analyzing next-generation sequencing data is difficult because datasets are large, second generation sequencing platforms have high error rates, and because each position in the target genome (exome, transcriptome, etc.) is sequenced multiple times. Given these challenges, numerous bioinformatic algorithms have been developed to analyze these data. These algorithms aim to find an appropriate balance between data loss, errors, analysis time, and memory footprint. Typical analysis pipelines require multiple steps. If one or more of these steps is unnecessary, it would significantly decrease compute time and data manipulation to remove the step. One step in many pipelines is PCR duplicate removal, where PCR duplicates arise from multiple PCR products from the same template molecule binding on the flowcell. These are often removed because there is concern they can lead to false positive variant calls. Picard (MarkDuplicates) and SAMTools (rmdup) are the two main softwares used for PCR duplicate removal. RESULTS: Approximately 92 % of the 17+ million variants called were called whether we removed duplicates with Picard or SAMTools, or left the PCR duplicates in the dataset. There were no significant differences between the unique variant sets when comparing the transition/transversion ratios (p = 1.0), percentage of novel variants (p = 0.99), average population frequencies (p = 0.99), and the percentage of protein-changing variants (p = 1.0). Results were similar for variants in the American College of Medical Genetics genes. Genotype concordance between NGS and SNP chips was above 99 % for all genotype groups (e.g., homozygous reference). CONCLUSIONS: Our results suggest that PCR duplicate removal has minimal effect on the accuracy of subsequent variant calls.

Automatic video browsing requires algorithms for detecting a variety of events, including production effects (e.g., scene breaks and captions) and moving objects. We present new methods that use edges and motion for detecting production effects and computing motion segmentation. Production effects, such as cuts, dissolves, wipes and captions, can be detected by looking for new edges that are far from previous edges. A global motion computation, is used to register consecutive images. We have also developed a method for motion segmentation, which does not require computing local optical flow. Our methods run at several frames per second on a Sparc workstation, and tolerate compression artifacts.

Color histograms are used to compare images in many applications. Their advantages are e#ciency, and insensitivity to small changes in camera viewpoint. However, color histograms lack spatial information, and this can cause images with very different appearances to have similar histograms. For example, a picture of fall foliage might contain a large number of scattered red pixels; this could have a similar color histogram to a picture of a single large red object. We describe a histogram-based method for comparing images that incorporates spatial information. While a color histogram counts the number of pixels with a given color, a color coherence vector #CCV# measures the spatial coherence of the pixels with a given color. If the red pixels in an image are members of large red regions, this color will have high coherence, while if the red pixels are widely scattered it will havelow coherence. CCV's can be computed at over 5 images per second on a standard workstation. A da...

No abstract available.