justin

Today I read a paper titled “Joint Belief and Intent Prediction for Collision Avoidance in Autonomous Vehicles”

The abstract is:
This paper describes a novel method for allowing an autonomous ground vehicle to predict the intent of other agents in an urban environment.

This method, termed the cognitive driving framework, models both the intent and the potentially false beliefs of an obstacle vehicle.

By modeling the relationships between these variables as a dynamic Bayesian network, filtering can be performed to calculate the intent of the obstacle vehicle as well as its belief about the environment.

This joint knowledge can be exploited to plan safer and more efficient trajectories when navigating in an urban environment.

Simulation results are presented that demonstrate the ability of the proposed method to calculate the intent of obstacle vehicles as an autonomous vehicle navigates a road intersection such that preventative maneuvers can be taken to avoid imminent collisions.

Today I read a paper titled “Control of Memory, Active Perception, and Action in Minecraft”

The abstract is:
In this paper, we introduce a new set of reinforcement learning (RL) tasks in Minecraft (a flexible 3D world).

We then use these tasks to systematically compare and contrast existing deep reinforcement learning (DRL) architectures with our new memory-based DRL architectures.

These tasks are designed to emphasize, in a controllable manner, issues that pose challenges for RL methods including partial observability (due to first-person visual observations), delayed rewards, high-dimensional visual observations, and the need to use active perception in a correct manner so as to perform well in the tasks.

While these tasks are conceptually simple to describe, by virtue of having all of these challenges simultaneously they are difficult for current DRL architectures.

Additionally, we evaluate the generalization performance of the architectures on environments not used during training.

The experimental results show that our new architectures generalize to unseen environments better than existing DRL architectures.

Today I read a paper titled “Determining the best attributes for surveillance video keywords generation”

The abstract is:
Automatic video keyword generation is one of the key ingredients in reducing the burden of security officers in analyzing surveillance videos.

Keywords or attributes are generally chosen manually based on expert knowledge of surveillance.

Most existing works primarily aim at either supervised learning approaches relying on extensive manual labelling or hierarchical probabilistic models that assume the features are extracted using the bag-of-words approach; thus limiting the utilization of the other features.

To address this, we turn our attention to automatic attribute discovery approaches.

However, it is not clear which automatic discovery approach can discover the most meaningful attributes.

Furthermore, little research has been done on how to compare and choose the best automatic attribute discovery methods.

In this paper, we propose a novel approach, based on the shared structure exhibited amongst meaningful attributes, that enables us to compare between different automatic attribute discovery approaches.We then validate our approach by comparing various attribute discovery methods such as PiCoDeS on two attribute datasets.

The evaluation shows that our approach is able to select the automatic discovery approach that discovers the most meaningful attributes.

We then employ the best discovery approach to generate keywords for videos recorded from a surveillance system.

This work shows it is possible to massively reduce the amount of manual work in generating video keywords without limiting ourselves to a particular video feature descriptor.

Today I read a paper titled “Feature Lines for Illustrating Medical Surface Models: Mathematical Background and Survey”

The abstract is:
This paper provides a tutorial and survey for a specific kind of illustrative visualization technique: feature lines.

We examine different feature line methods.

For this, we provide the differential geometry behind these concepts and adapt this mathematical field to the discrete differential geometry.

All discrete differential geometry terms are explained for triangulated surface meshes.

These utilities serve as basis for the feature line methods.

We provide the reader with all knowledge to re-implement every feature line method.

Furthermore, we summarize the methods and suggest a guideline for which kind of surface which feature line algorithm is best suited.

Our work is motivated by, but not restricted to, medical and biological surface models.

Today I read a paper titled “The Information-Collecting Vehicle Routing Problem: Stochastic Optimization for Emergency Storm Response”

The abstract is:
Utilities face the challenge of responding to power outages due to storms and ice damage, but most power grids are not equipped with sensors to pinpoint the precise location of the faults causing the outage.

Instead, utilities have to depend primarily on phone calls (trouble calls) from customers who have lost power to guide the dispatching of utility trucks.

In this paper, we develop a policy that routes a utility truck to restore outages in the power grid as quickly as possible, using phone calls to create beliefs about outages, but also using utility trucks as a mechanism for collecting additional information.

This means that routing decisions change not only the physical state of the truck (as it moves from one location to another) and the grid (as the truck performs repairs), but also our belief about the network, creating the first stochastic vehicle routing problem that explicitly models information collection and belief modeling.

We address the problem of managing a single utility truck, which we start by formulating as a sequential stochastic optimization model which captures our belief about the state of the grid.

We propose a stochastic lookahead policy, and use Monte Carlo tree search (MCTS) to produce a practical policy that is asymptotically optimal.

Simulation results show that the developed policy restores the power grid much faster compared to standard industry heuristics.

Today I read a paper titled “Relating Cascaded Random Forests to Deep Convolutional Neural Networks for Semantic Segmentation”

The abstract is:
We consider the task of pixel-wise semantic segmentation given a small set of labeled training images.

Among two of the most popular techniques to address this task are Random Forests (RF) and Neural Networks (NN).

The main contribution of this work is to explore the relationship between two special forms of these techniques: stacked RFs and deep Convolutional Neural Networks (CNN).

We show that there exists a mapping from stacked RF to deep CNN, and an approximate mapping back.

This insight gives two major practical benefits: Firstly, deep CNNs can be intelligently constructed and initialized, which is crucial when dealing with a limited amount of training data.

Secondly, it can be utilized to create a new stacked RF with improved performance.

Furthermore, this mapping yields a new CNN architecture, that is well suited for pixel-wise semantic labeling.

We experimentally verify these practical benefits for two different application scenarios in computer vision and biology, where the layout of parts is important: Kinect-based body part labeling from depth images, and somite segmentation in microscopy images of developing zebrafish.

Today I read a paper titled “Where’s My Drink? Enabling Peripheral Real World Interactions While Using HMDs”

The abstract is:
Head Mounted Displays (HMDs) allow users to experience virtual reality with a great level of immersion.

However, even simple physical tasks like drinking a beverage can be difficult and awkward while in a virtual reality experience.

We explore mixed reality renderings that selectively incorporate the physical world into the virtual world for interactions with physical objects.

We conducted a user study comparing four rendering techniques that balances immersion in a virtual world with ease of interaction with the physical world.

Finally, we discuss the pros and cons of each approach, suggesting guidelines for future rendering techniques that bring physical objects into virtual reality.

Today I read a paper titled “Usability Engineering of Games: A Comparative Analysis of Measuring Excitement Using Sensors, Direct Observations and Self-Reported Data”

The abstract is:
Usability engineering and usability testing are concepts that continue to evolve.

Interesting research studies and new ideas come up every now and then.

This paper tests the hypothesis of using an EDA based physiological measurements as a usability testing tool by considering three measures which are observers opinions, self reported data and EDA based physiological sensor data.

These data were analyzed comparatively and statistically.

It concludes by discussing the findings that has been obtained from those subjective and objective measures, which partially supports the hypothesis.

Today I read a paper titled “Detecting and avoiding frontal obstacles from monocular camera for micro unmanned aerial vehicles”

The abstract is:
In literature, several approaches are trying to make the UAVs fly autonomously i.e., by extracting perspective cues such as straight lines.

However, it is only available in well-defined human made environments, in addition to many other cues which require enough texture information.

Our main target is to detect and avoid frontal obstacles from a monocular camera using a quad rotor Ar.Drone 2 by exploiting optical flow as a motion parallax, the drone is permitted to fly at a speed of 1 m/s and an altitude ranging from 1 to 4 meters above the ground level.

In general, detecting and avoiding frontal obstacle is a quite challenging problem because optical flow has some limitation which should be taken into account i.e.

lighting conditions and aperture problem.

Today I read a paper titled “Unscented Bayesian Optimization for Safe Robot Grasping”

The abstract is:
We address the robot grasp optimization problem of unknown objects considering uncertainty in the input space.

Grasping unknown objects can be achieved by using a trial and error exploration strategy.

Bayesian optimization is a sample efficient optimization algorithm that is especially suitable for this setups as it actively reduces the number of trials for learning about the function to optimize.

In fact, this active object exploration is the same strategy that infants do to learn optimal grasps.

One problem that arises while learning grasping policies is that some configurations of grasp parameters may be very sensitive to error in the relative pose between the object and robot end-effector.

We call these configurations unsafe because small errors during grasp execution may turn good grasps into bad grasps.

Therefore, to reduce the risk of grasp failure, grasps should be planned in safe areas.

We propose a new algorithm, Unscented Bayesian optimization that is able to perform sample efficient optimization while taking into consideration input noise to find safe optima.

The contribution of Unscented Bayesian optimization is twofold as if provides a new decision process that drives exploration to safe regions and a new selection procedure that chooses the optimal in terms of its safety without extra analysis or computational cost.

Both contributions are rooted on the strong theory behind the unscented transformation, a popular nonlinear approximation method.

We show its advantages with respect to the classical Bayesian optimization both in synthetic problems and in realistic robot grasp simulations.

The results highlights that our method achieves optimal and robust grasping policies after few trials while the selected grasps remain in safe regions.

Today I read a paper titled “Some Experimental Issues in Financial Fraud Detection: An Investigation”

The abstract is:
Financial fraud detection is an important problem with a number of design aspects to consider.

Issues such as algorithm selection and performance analysis will affect the perceived ability of proposed solutions, so for auditors and re-searchers to be able to sufficiently detect financial fraud it is necessary that these issues be thoroughly explored.

In this paper we will revisit the key performance metrics used for financial fraud detection with a focus on credit card fraud, critiquing the prevailing ideas and offering our own understandings.

There are many different performance metrics that have been employed in prior financial fraud detection research.

We will analyse several of the popular metrics and compare their effectiveness at measuring the ability of detection mechanisms.

We further investigated the performance of a range of computational intelligence techniques when applied to this problem domain, and explored the efficacy of several binary classification methods.

Today I read a paper titled “Data Driven Robust Image Guided Depth Map Restoration”

The abstract is:
Depth maps captured by modern depth cameras such as Kinect and Time-of-Flight (ToF) are usually contaminated by missing data, noises and suffer from being of low resolution.

In this paper, we present a robust method for high-quality restoration of a degraded depth map with the guidance of the corresponding color image.

We solve the problem in an energy optimization framework that consists of a novel robust data term and smoothness term.

To accommodate not only the noise but also the inconsistency between depth discontinuities and the color edges, we model both the data term and smoothness term with a robust exponential error norm function.

We propose to use Iteratively Re-weighted Least Squares (IRLS) methods for efficiently solving the resulting highly non-convex optimization problem.

More importantly, we further develop a data-driven adaptive parameter selection scheme to properly determine the parameter in the model.

We show that the proposed approach can preserve fine details and sharp depth discontinuities even for a large upsampling factor ($8\times$ for example).

Experimental results on both simulated and real datasets demonstrate that the proposed method outperforms recent state-of-the-art methods in coping with the heavy noise, preserving sharp depth discontinuities and suppressing the texture copy artifacts.

Today I read a paper titled “Watch-n-Patch: Unsupervised Learning of Actions and Relations”

The abstract is:
There is a large variation in the activities that humans perform in their everyday lives.

We consider modeling these composite human activities which comprises multiple basic level actions in a completely unsupervised setting.

Our model learns high-level co-occurrence and temporal relations between the actions.

We consider the video as a sequence of short-term action clips, which contains human-words and object-words.

An activity is about a set of action-topics and object-topics indicating which actions are present and which objects are interacting with.

We then propose a new probabilistic model relating the words and the topics.

It allows us to model long-range action relations that commonly exist in the composite activities, which is challenging in previous works.

We apply our model to the unsupervised action segmentation and clustering, and to a novel application that detects forgotten actions, which we call action patching.

For evaluation, we contribute a new challenging RGB-D activity video dataset recorded by the new Kinect v2, which contains several human daily activities as compositions of multiple actions interacting with different objects.

Moreover, we develop a robotic system that watches people and reminds people by applying our action patching algorithm.

Our robotic setup can be easily deployed on any assistive robot.

Today I read a paper titled “Assessing 3D scan quality through paired-comparisons psychophysics test”

The abstract is:
Consumer 3D scanners and depth cameras are increasingly being used to generate content and avatars for Virtual Reality (VR) environments and avoid the inconveniences of hand modeling; however, it is sometimes difficult to evaluate quantitatively the mesh quality at which 3D scans should be exported, and whether the object perception might be affected by its shading.

We propose using a paired-comparisons test based on psychophysics of perception to do that evaluation.

As psychophysics is not subject to opinion, skill level, mental state, or economic situation it can be considered a quantitative way to measure how people perceive the mesh quality.

In particular, we propose using the psychophysical measure for the comparison of four different levels of mesh quality (1K, 5K, 10K and 20K triangles).

We present two studies within subjects: in one we investigate the quality perception variations of seeing an object in a regular screen monitor against an stereoscopic Head Mounted Display (HMD); while in the second experiment we aim at detecting the effects of shading into quality perception.

At each iteration of the pair-test comparisons participants pick the mesh that they think had higher quality; by the end of the experiment we compile a preference matrix.

The matrix evidences the correlation between real quality and assessed quality.

Regarding the shading mode, we find an interaction with quality and shading when the model has high definition.

Furthermore, we assess the subjective realism of the most/least preferred scans using an Immersive Augmented Reality (IAR) video-see-through setup.

Results show higher levels of realism were perceived through the HMD than when using a monitor, although the quality was similarly perceived in both systems.

Today I read a paper titled “Contextual Media Retrieval Using Natural Language Queries”

The abstract is:
The widespread integration of cameras in hand-held and head-worn devices as well as the ability to share content online enables a large and diverse visual capture of the world that millions of users build up collectively every day.

We envision these images as well as associated meta information, such as GPS coordinates and timestamps, to form a collective visual memory that can be queried while automatically taking the ever-changing context of mobile users into account.

As a first step towards this vision, in this work we present Xplore-M-Ego: a novel media retrieval system that allows users to query a dynamic database of images and videos using spatio-temporal natural language queries.

We evaluate our system using a new dataset of real user queries as well as through a usability study.

One key finding is that there is a considerable amount of inter-user variability, for example in the resolution of spatial relations in natural language utterances.

We show that our retrieval system can cope with this variability using personalisation through an online learning-based retrieval formulation.

Today I read a paper titled “An Improved Tracking using IMU and Vision Fusion for Mobile Augmented Reality Applications”

The abstract is:
Mobile Augmented Reality (MAR) is becoming an important cyber-physical system application given the ubiquitous availability of mobile phones.

With the need to operate in unprepared environments, accurate and robust registration and tracking has become an important research problem to solve.

In fact, when MAR is used for tele-interactive applications involving large distances, say from an accident site to insurance office, tracking at both the ends is desirable and further it is essential to appropriately fuse inertial and vision sensors data.

In this paper, we present results and discuss some insights gained in marker-less tracking during the development of a prototype pertaining to an example use case related to breakdown or damage assessment of a vehicle.

The novelty of this paper is in bringing together different components and modules with appropriate enhancements towards a complete working system.

Today I read a paper titled “Perceiving Mass in Mixed Reality through Pseudo-Haptic Rendering of Newton’s Third Law”

The abstract is:
In mixed reality, real objects can be used to interact with virtual objects.

However, unlike in the real world, real objects do not encounter any opposite reaction force when pushing against virtual objects.

The lack of reaction force during manipulation prevents users from perceiving the mass of virtual objects.

Although this could be addressed by equipping real objects with force-feedback devices, such a solution remains complex and impractical.In this work, we present a technique to produce an illusion of mass without any active force-feedback mechanism.

This is achieved by simulating the effects of this reaction force in a purely visual way.

A first study demonstrates that our technique indeed allows users to differentiate light virtual objects from heavy virtual objects.

In addition, it shows that the illusion is immediately effective, with no prior training.

In a second study, we measure the lowest mass difference (JND) that can be perceived with this technique.

The effectiveness and ease of implementation of our solution provides an opportunity to enhance mixed reality interaction at no additional cost.