Semantic aware reconstruction is more advantageous than geometric-only reconstruction for future robotic and AR/VR applications because it represents not only where things are, but also what things are. Object-centric mapping is a task to build an object-level reconstruction where objects are separate and meaningful entities that convey both geometry and semantic information. In this paper, we present MO-LTR, a solution to object-centric mapping using only monocular image sequences and camera poses. It is able to localize, track, and reconstruct multiple objects in an online fashion when an RGB camera captures a video of the surrounding. Given a new RGB frame, MO-LTR firstly applies a monocular 3D detector to localize objects of interest and extract their shape codes that represent the object shape in a learned embedding space. Detections are then merged to existing objects in the map after data association. Motion state (i.e. kinematics and the motion status) of each object is tracked by a multiple model Bayesian filter and object shape is progressively refined by fusing multiple shape code. We evaluate localization, tracking, and reconstruction on benchmarking datasets for indoor and outdoor scenes, and show superior performance over previous approaches.
Performance evaluation is indispensable to the advancement of machine vision, yet its consistency and rigour have not received proportionate attention. This paper examines performance evaluation criteria for basic vision tasks namely, object detection, instance-level segmentation and multi-object tracking. Specifically, we advocate the use of criteria that are (i) consistent with mathematical requirements such as the metric properties, (ii) contextually meaningful in sanity tests, and (iii) robust to hyper-parameters for reliability. We show that many widely used performance criteria do not fulfill these requirements. Moreover, we explore alternative criteria for detection, segmentation, and tracking, using metrics for sets of shapes, and assess them against these requirements.
Tracking and locating radio-tagged wildlife is a labor-intensive and time-consuming task necessary in wildlife conservation. In this article, we focus on the problem of achieving embedded autonomy for a resource-limited aerial robot for the task capable of avoiding undesirable disturbances to wildlife. We employ a lightweight sensor system capable of simultaneous (noisy) measurements of radio signal strength information from multiple tags for estimating object locations. We formulate a new lightweight task-based trajectory planning method-LAVAPilot-with a greedy evaluation strategy and a void functional formulation to achieve situational awareness to maintain a safe distance from objects of interest. Conceptually, we embed our intuition of moving closer to reduce the uncertainty of measurements into LAVAPilot instead of employing a computationally intensive information gain based planning strategy. We employ LAVAPilot and the sensor to build a lightweight aerial robot platform with fully embedded autonomy for jointly tracking and planning to track and locate multiple VHF radio collar tags used by conservation biologists. Using extensive Monte Carlo simulation-based experiments, implementations on a single board compute module, and field experiments using an aerial robot platform with multiple VHF radio collar tags, we evaluate our joint planning and tracking algorithms. Further, we compare our method with other information-based planning methods with and without situational awareness to demonstrate the effectiveness of our robot executing LAVAPilot. Our experiments demonstrate that LAVAPilot significantly reduces (by 98.5%) the computational cost of planning to enable real-time planning decisions whilst achieving similar localization accuracy of objects compared to information gain based planning methods, albeit taking a slightly longer time to complete a mission.
Wearables are fundamental to improving our understanding of human activities, especially for an increasing number of healthcare applications from rehabilitation to fine-grained gait analysis. Although our collective know-how to solve Human Activity Recognition (HAR) problems with wearables has progressed immensely with end-to-end deep learning paradigms, several fundamental opportunities remain overlooked. We rigorously explore these new opportunities to learn enriched and highly discriminating activity representations. We propose: i) learning to exploit the latent relationships between multi-channel sensor modalities and specific activities; ii) investigating the effectiveness of data-agnostic augmentation for multi-modal sensor data streams to regularize deep HAR models; and iii) incorporating a classification loss criterion to encourage minimal intra-class representation differences whilst maximising inter-class differences to achieve more discriminative features. Our contributions achieves new state-of-the-art performance on four diverse activity recognition problem benchmarks with large margins -- with up to 6% relative margin improvement. We extensively validate the contributions from our design concepts through extensive experiments, including activity misalignment measures, ablation studies and insights shared through both quantitative and qualitative studies.
Smooth and seamless robot navigation while interacting with humans depends on predicting human movements. Forecasting such human dynamics often involves modeling human trajectories (global motion) or detailed body joint movements (local motion). Prior work typically tackled local and global human movements separately. In this paper, we propose a novel framework to tackle both tasks of human motion (or trajectory) and body skeleton pose forecasting in a unified end-to-end pipeline. To deal with this real-world problem, we consider incorporating both scene and social contexts, as critical clues for this prediction task, into our proposed framework. To this end, we first couple these two tasks by i) encoding their history using a shared Gated Recurrent Unit (GRU) encoder and ii) applying a metric as loss, which measures the source of errors in each task jointly as a single distance. Then, we incorporate the scene context by encoding a spatio-temporal representation of the video data. We also include social clues by generating a joint feature representation from motion and pose of all individuals from the scene using a social pooling layer. Finally, we use a GRU based decoder to forecast both motion and skeleton pose. We demonstrate that our proposed framework achieves a superior performance compared to several baselines on two social datasets.
The state-of-the art solutions for human activity understanding from a video stream formulate the task as a spatio-temporal problem which requires joint localization of all individuals in the scene and classification of their actions or group activity over time. Who is interacting with whom, e.g. not everyone in a queue is interacting with each other, is often not predicted. There are scenarios where people are best to be split into sub-groups, which we call social groups, and each social group may be engaged in a different social activity. In this paper, we solve the problem of simultaneously grouping people by their social interactions, predicting their individual actions and the social activity of each social group, which we call the social task. Our main contributions are: i) we propose an end-to-end trainable framework for the social task; ii) our proposed method also sets the state-of-the-art results on two widely adopted benchmarks for the traditional group activity recognition task (assuming individuals of the scene form a single group and predicting a single group activity label for the scene); iii) we introduce new annotations on an existing group activity dataset, re-purposing it for the social task.
Standardized benchmarks are crucial for the majority of computer vision applications. Although leaderboards and ranking tables should not be over-claimed, benchmarks often provide the most objective measure of performance and are therefore important guides for research. The benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal to establish a standardized evaluation of multiple object tracking methods. The challenge focuses on multiple people tracking, since pedestrians are well studied in the tracking community, and precise tracking and detection has high practical relevance. Since the first release, MOT15, MOT16, and MOT17 have tremendously contributed to the community by introducing a clean dataset and precise framework to benchmark multi-object trackers. In this paper, we present our MOT20benchmark, consisting of 8 new sequences depicting very crowded challenging scenes. The benchmark was presented first at the 4thBMTT MOT Challenge Workshop at the Computer Vision and Pattern Recognition Conference (CVPR) 2019, and gives to chance to evaluate state-of-the-art methods for multiple object tracking when handling extremely crowded scenarios.
An autonomous navigating agent needs to perceive and track the motion of objects and other agents in its surroundings to achieve robust and safe motion planning and execution. While autonomous navigation requires a multi-object tracking (MOT) system to provide 3D information, most research has been done in 2D MOT from RGB videos. In this work we present JRMOT, a novel 3D MOT system that integrates information from 2D RGB images and 3D point clouds into a real-time performing framework. Our system leverages advancements in neural-network based re-identification as well as 2D and 3D detection and descriptors. We incorporate this into a joint probabilistic data-association framework within a multi-modal recursive Kalman architecture to achieve online, real-time 3D MOT. As part of our work, we release the JRDB dataset, a novel large scale 2D+3D dataset and benchmark annotated with over 2 million boxes and 3500 time consistent 2D+3D trajectories across 54 indoor and outdoor scenes. The dataset contains over 60 minutes of data including 360 degree cylindrical RGB video and 3D pointclouds. The presented 3D MOT system demonstrates state-of-the-art performance against competing methods on the popular 2D tracking KITTI benchmark and serves as a competitive 3D tracking baseline for our dataset and benchmark.
This paper addresses the task of set prediction using deep feed-forward neural networks. A set is a collection of elements which is invariant under permutation and the size of a set is not fixed in advance. Many real-world problems, such as image tagging and object detection, have outputs that are naturally expressed as sets of entities. This creates a challenge for traditional deep neural networks which naturally deal with structured outputs such as vectors, matrices or tensors. We present a novel approach for learning to predict sets with unknown permutation and cardinality using deep neural networks. In our formulation we define a likelihood for a set distribution represented by a) two discrete distributions defining the set cardinally and permutation variables, and b) a joint distribution over set elements with a fixed cardinality. Depending on the problem under consideration, we define different training models for set prediction using deep neural networks. We demonstrate the validity of our set formulations on relevant vision problems such as: 1)multi-label image classification where we achieve state-of-the-art performance on the PASCAL VOC and MS COCO datasets, 2) object detection, for which our formulation outperforms state-of-the-art detectors such as Faster R-CNN and YOLO v3, and 3) a complex CAPTCHA test, where we observe that, surprisingly, our set-based network acquired the ability of mimicking arithmetics without any rules being coded.