Tim K. Marks

An improved deep learning architecture for person re-identification

In this work, we propose a method for simultaneously learning features and a corresponding similarity metric for person re-identification. We present a deep convolutional architecture with layers specially designed to address the problem of re-identification. Given a pair of images as input, our network outputs a similarity value indicating whether the two input images depict the same person. Novel elements of our architecture include a layer that computes cross-input neighborhood differences, which capture local relationships between the two input images based on mid-level features from each input image. A high-level summary of the outputs of this layer is computed by a layer of patch summary features, which are then spatially integrated in subsequent layers. Our method significantly outperforms the state of the art on both a large data set (CUHK03) and a medium-sized data set (CUHK01), and is resistant to over-fitting. We also demonstrate that by initially training on an unrelated large data set before fine-tuning on a small target data set, our network can achieve results comparable to the state of the art even on a small data set (VIPeR).

Fully automatic pose-invariant face recognition via 3D pose normalization

An ideal approach to the problem of pose-invariant face recognition would handle continuous pose variations, would not be database specific, and would achieve high accuracy without any manual intervention. Most of the existing approaches fail to match one or more of these goals. In this paper, we present a fully automatic system for pose-invariant face recognition that not only meets these requirements but also outperforms other comparable methods. We propose a 3D pose normalization method that is completely automatic and leverages the accurate 2D facial feature points found by the system. The current system can handle 3D pose variation up to ±45° in yaw and ±30° in pitch angles. Recognition experiments were conducted on the USF 3D, Multi-PIE, CMU-PIE, FERET, and FacePix databases. Our system not only shows excellent generalization by achieving high accuracy on all 5 databases but also outperforms other methods convincingly.

Fast object localization and pose estimation in heavy clutter for robotic bin picking

We present a practical vision-based robotic bin-picking system that performs detection and three-dimensional pose estimation of objects in an unstructured bin using a novel camera design, picks up parts from the bin, and performs error detection and pose correction while the part is in the gripper. Two main innovations enable our system to achieve real-time robust and accurate operation. First, we use a multi-flash camera that extracts robust depth edges. Second, we introduce an efficient shape-matching algorithm called fast directional chamfer matching (FDCM), which is used to reliably detect objects and estimate their poses. FDCM improves the accuracy of chamfer matching by including edge orientation. It also achieves massive improvements in matching speed using line-segment approximations of edges, a three-dimensional distance transform, and directional integral images. We empirically show that these speedups, combined with the use of bounds in the spatial and hypothesis domains, give the algorithm sublinear computational complexity. We also apply our FDCM method to other applications in the context of deformable and articulated shape matching. In addition to significantly improving upon the accuracy of previous chamfer matching methods in all of the evaluated applications, FDCM is up to two orders of magnitude faster than the previous methods.

Real-time 3D head pose and facial landmark estimation from depth images using triangular surface patch features

We present a real-time system for 3D head pose estimation and facial landmark localization using a commodity depth sensor. We introduce a novel triangular surface patch (TSP) descriptor, which encodes the shape of the 3D surface of the face within a triangular area. The proposed descriptor is viewpoint invariant, and it is robust to noise and to variations in the data resolution. Using a fast nearest neighbor lookup, TSP descriptors from an input depth map are matched to the most similar ones that were computed from synthetic head models in a training phase. The matched triangular surface patches in the training set are used to compute estimates of the 3D head pose and facial landmark positions in the input depth map. By sampling many TSP descriptors, many votes for pose and landmark positions are generated which together yield robust final estimates. We evaluate our approach on the publicly available Biwi Kinect Head Pose Database to compare it against state-of-the-art methods. Our results show a significant improvement in the accuracy of both pose and landmark location estimates while maintaining real-time speed.

Robust Face Alignment Using a Mixture of Invariant Experts

Face alignment, which is the task of finding the locations of a set of facial landmark points in an image of a face, is useful in widespread application areas. Face alignment is particularly challenging when there are large variations in pose (in-plane and out-of-plane rotations) and facial expression. To address this issue, we propose a cascade in which each stage consists of a mixture of regression experts. Each expert learns a customized regression model that is specialized to a different subset of the joint space of pose and expressions. The system is invariant to a predefined class of transformations (e.g., affine), because the input is transformed to match each experts prototype shape before the regression is applied. We also present a method to include deformation constraints within the discriminative alignment framework, which makes our algorithm more robust. Our algorithm significantly outperforms previous methods on publicly available face alignment datasets.

P2Π: a minimal solution for registration of 3D points to 3D planes

This paper presents a class of minimal solutions for the 3D-to-3D registration problem in which the sensor data are 3D points and the corresponding object data are 3D planes. In order to compute the 6 degrees-of-freedom transformation between the sensor and the object, we need at least six points on three or more planes. We systematically investigate and develop pose estimation algorithms for several configurations, including all minimal configurations, that arise from the distribution of points on planes. The degenerate configurations are also identified. We point out that many existing and unsolved 2D-to-3D and 3D-to-3D pose estimation algorithms involving points, lines, and planes can be transformed into the problem of registering points to planes. In addition to simulations, we also demonstrate the algorithms effectiveness in two real-world applications: registration of a robotic arm with an object using a contact sensor, and registration of 3D point clouds that were obtained using multi-view reconstruction of planar city models.

Morphable Reflectance Fields for enhancing face recognition

In this paper, we present a novel framework to address the confounding effects of illumination variation in face recognition. By augmenting the gallery set with realistically relit images, we enhance recognition performance in a classifier-independent way. We describe a novel method for single-image relighting, Morphable Reflectance Fields (MoRF), which does not require manual intervention and provides relighting superior to that of existing automatic methods. We test our framework through face recognition experiments using various state-of-the-art classifiers and popular benchmark datasets: CMU PIE, Multi-PIE, and MERL Dome. We demonstrate that our MoRF relighting and gallery augmentation framework achieves improvements in terms of both rank-1 recognition rates and ROC curves. We also compare our model with other automatic relighting methods to confirm its advantage. Finally, we show that the recognition rates achieved using our framework exceed those of state-of-the-art recognizers on the aforementioned databases.

Entropy-based motion selection for Touch-based registration using Rao-Blackwellized particle filtering

Registering an object with respect to a robots coordinate system is essential to industrial assembly tasks such as grasping and insertion. Touch-based registration algorithms use a probe attached to a robot to measure the positions of contact, then use these measurements to register the robot to a model of the object. In existing work on touch-based registration, the selection of contact positions is not typically addressed. We present an algorithm for selecting the next robot motion to maximize the expected information obtained by the resulting contact with the object. Our method performs 6-DOF registration in a Rao-Blackwellized particle filtering (RBPF) framework. Using the 3D model of the object and the current RBPF distribution, we compute the expected information gain from a proposed robot motion by estimating the expected entropy that the RBPF distribution would have as a result of being updated by the proposed motion. The motion that provides the maximum information gain is selected and used for the next measurement, and the process is repeated. We compare various methods for estimating entropy, including approximations based on kernel density estimation. We demonstrate entropy-based motion selection in fully automatic and human-guided registration, both in simulations and on a real robotic platform.

Rao-Blackwellized particle filtering for probing-based 6-DOF localization in robotic assembly

This paper presents a probing-based method for probabilistic localization in automated robotic assembly. We consider peg-in-hole problems in which a needle-like peg has a single point of contact with the object that contains the hole, and in which the initial uncertainty in the relative pose (3D position and 3D angle) between the peg and the object is much greater than the required accuracy (assembly clearance). We solve this 6 degree-of-freedom (6-DOF) localization problem using a Rao-Blackwellized particle filter, in which the probability distribution over the pegs pose is factorized into two components: The distribution over position (3-DOF) is represented by particles, while the distribution over angle (3-DOF) is approximated as a Gaussian distribution for each particle, updated using an extended Kalman filter. This factorization reduces the number of particles required for localization by orders of magnitude, enabling real-time online 6-DOF pose estimation. Each measurement is simply the contact position obtained by randomly repositioning the peg and moving towards the object until there is contact. To compute the likelihood of each measurement, we use as a map a mesh model of the object that is based on the CAD model but also explicitly models the uncertainty in the map. The mesh uncertainty model makes our system robust to cases in which the actual measurement is different from the expected one. We demonstrate the advantages of our approach over previous methods using simulations as well as physical experiments with a robotic arm and a metal peg and object.

High-accuracy user identification using EEG biometrics

We analyze brain waves acquired through a consumer-grade EEG device to investigate its capabilities for user identification and authentication. First, we show the statistical significance of the P300 component in event-related potential (ERP) data from 14-channel EEGs across 25 subjects. We then apply a variety of machine learning techniques, comparing the user identification performance of various different combinations of a dimensionality reduction technique followed by a classification algorithm. Experimental results show that an identification accuracy of 72% can be achieved using only a single 800 ms ERP epoch. In addition, we demonstrate that the user identification accuracy can be significantly improved to more than 96.7% by joint classification of multiple epochs.