Metric learning aims to construct an embedding where two extracted features corresponding to the same identity are likely to be closer than features from different identities. This paper presents a ...method for learning such a feature space where the cosine similarity is effectively optimized through a simple re-parametrization of the conventional softmax classification regime. At test time, the final classification layer can be stripped from the network to facilitate nearest neighbor queries on unseen individuals using the cosine similarity metric. This approach presents a simple alternative to direct metric learning objectives such as siamese networks that have required sophisticated pair or triplet sampling strategies in the past. The method is evaluated on two large-scale pedestrian re-identification datasets where competitive results are achieved overall. In particular, we achieve better generalization on the test set compared to a network trained with triplet loss.
Simple Online and Realtime Tracking (SORT) is a pragmatic approach to multiple object tracking with a focus on simple, effective algorithms. In this paper, we integrate appearance information to ...improve the performance of SORT. Due to this extension we are able to track objects through longer periods of occlusions, effectively reducing the number of identity switches. In spirit of the original framework we place much of the computational complexity into an offline pre-training stage where we learn a deep association metric on a largescale person re-identification dataset. During online application, we establish measurement-to-track associations using nearest neighbor queries in visual appearance space. Experimental evaluation shows that our extensions reduce the number of identity switches by 45%, achieving overall competitive performance at high frame rates.
Simple online and realtime tracking Bewley, Alex; Zongyuan Ge; Ott, Lionel ...
2016 IEEE International Conference on Image Processing (ICIP),
2016-Sept.
Conference Proceeding
This paper explores a pragmatic approach to multiple object tracking where the main focus is to associate objects efficiently for online and realtime applications. To this end, detection quality is ...identified as a key factor influencing tracking performance, where changing the detector can improve tracking by up to 18.9%. Despite only using a rudimentary combination of familiar techniques such as the Kalman Filter and Hungarian algorithm for the tracking components, this approach achieves an accuracy comparable to state-of-the-art online trackers. Furthermore, due to the simplicity of our tracking method, the tracker updates at a rate of 260 Hz which is over 20x faster than other state-of-the-art trackers.
Appearance changes due to weather and seasonal conditions represent a strong impediment to the robust implementation of machine learning systems in outdoor robotics. While supervised learning ...optimises a model for the training domain, it will deliver degraded performance in application domains that underlie distributional shifts caused by these changes. Traditionally, this problem has been addressed via the collection of labelled data in multiple domains or by imposing priors on the type of shift between both domains. We frame the problem in the context of unsupervised domain adaptation and develop a framework for applying adversarial techniques to adapt popular, state-of-the-art network architectures with the additional objective to align features across domains. Moreover, as adversarial training is notoriously unstable, we first perform an extensive ablation study, adapting many techniques known to stabilise generative adversarial networks, and evaluate on a surrogate classification task with the same appearance change. The distilled insights are applied to the problem of free-space segmentation for motion planning in autonomous driving.
This paper addresses the problem of detecting people and vehicles on a surface mine by presenting an architecture that combines the complementary strengths of deep convolutional networks (DCN) with ...cluster‐based analysis. We highlight that using a DCN in a naïve black box approach results in a significantly high rate of errors due to the lack of mining‐specific training data and the unique landscape in a mine site. In this work, we propose a background model that exploits the abundance of background‐only images to discover the natural clusters in visual appearance using features extracted from the DCN. Both a simple nearest cluster‐based background model and an extended model with cosine features are investigated for their ability to identify and suppress potential false positives made by the DCN. Furthermore, localization of objects of interest is enabled through region proposals, which have been tuned to increase recall within the constraints of a computational budget. Finally, a soft fusion framework is presented to combine the estimates of both the DCN and background model to improve the accuracy of the detection. Our system is tested on over 11 km of real mine site data in both day and night conditions where we were able to detect both light and heavy vehicles along with mining personnel. We show that the introduction of our background model improves the detection performance. In particular, soft fusion of the background model and the DCN output produces a relative improvement in the F1 score of 46% and 28% compared to a baseline pretrained DCN and a DCN retrained with mining images, respectively.
The detection of 3D objects from LiDAR data is a critical component in most autonomous driving systems. Safe, high speed driving needs larger detection ranges, which are enabled by new LiDARs. These ...larger detection ranges require more efficient and accurate detection models. Towards this goal, we propose Range Sparse Net (RSN) - a simple, efficient, and accurate 3D object detector - in order to tackle real time 3D object detection in this extended detection regime. RSN predicts foreground points from range images and applies sparse convolutions on the selected foreground points to detect objects. The lightweight 2D convolutions on dense range images results in significantly fewer selected foreground points, thus enabling the later sparse convolutions in RSN to efficiently operate. Combining features from the range image further enhance detection accuracy. RSN runs at more than 60 frames per second on a 150m × 150m detection region on Waymo Open Dataset (WOD) while being more accurate than previously published detectors. As of 11/2020, RSN is ranked first in the WOD leaderboard based on the APH/LEVEL_1 metrics for LiDAR-based pedestrian and vehicle detection, while being several times faster than alternatives.
We provide the theory and the system needed to create large-scale dense reconstructions for mobile-robotics applications: this stands in contrast to the object-centric reconstructions dominant in the ...literature. Our BOR2G system fuses data from multiple sensor modalities (cameras, lidars, or both) and regularizes the resulting 3D model. We use a compressed 3D data structure, which allows us to operate over a large scale. In addition, because of the paucity of surface observations by the camera and lidar sensors, we regularize over both two (camera depth maps) and three dimensions (voxel grid) to provide a local contextual prior for the reconstruction. Our regularizer reduces the median error between 27% and 36% in 7.3 km of dense reconstructions with a median accuracy between 4 and 8 cm. Our pipeline does not end with regularization. We take the unusual step to apply a learned correction mechanism that takes the global context of the reconstruction and adjusts the constructed mesh, addressing errors that are pathological to the first-pass camera-derived reconstruction. We evaluate our system using the Stanford Burghers of Calais, Imperial College ICL-NUIM, Oxford Broad Street (released with this paper), and the KITTI datasets. These latter datasets see us operating at a combined scale and accuracy not seen in the literature. We provide statistics for the metric errors in all surfaces created compared with those measured with 3D lidar as ground truth. We demonstrate our system in practice by reconstructing the inside of the EUROfusion Joint European Torus (JET) fusion reactor, located at the Culham Centre for Fusion Energy (UK Atomic Energy Authority) in Oxfordshire.
Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models. While unsupervised domain adaptation aims to address ...this challenge, current approaches do not utilise the continuity of the occurring shifts. In particular, many robotics applications exhibit these conditions and thus facilitate the potential to incrementally adapt a learnt model over minor shifts which integrate to massive differences over time. Our work presents an adversarial approach for lifelong, incremental domain adaptation which benefits from unsupervised alignment to a series of intermediate domains which successively diverge from the labelled source domain. We empirically demonstrate that our incremental approach improves handling of large appearance changes, e.g. day to night, on a traversable-path segmentation task compared with a direct, single alignment step approach. Furthermore, by approximating the feature distribution for the source domain with a generative adversarial network, the deployment module can be rendered fully independent of retaining potentially large amounts of the related source training data for only a minor reduction in performance.
Anticipating the motion of all humans in dynamic environments such as homes and offices is critical to enable safe and effective robot navigation. Such spaces remain challenging as humans do not ...follow strict rules of motion and there are often multiple occluded entry points such as corners and doors that create opportunities for sudden encounters. In this work, we present a Transformer based architecture to predict human future trajectories in human-centric environments from input features including human positions, head orientations, and 3D skeletal keypoints from onboard in-the-wild sensory information. The resulting model captures the inherent uncertainty for future human trajectory prediction and achieves state-of-the-art performance on common prediction benchmarks and a human tracking dataset captured from a mobile robot adapted for the prediction task. Furthermore, we identify new agents with limited historical data as a major contributor to error and demonstrate the complementary nature of 3D skeletal poses in reducing prediction error in such challenging scenarios.
This paper is about enabling robots to improve their perceptual performance through repeated use in their operating environment, creating local expert detectors fitted to the places through which a ...robot moves. We leverage the concept of `experiences' in visual perception for robotics, accounting for bias in the data a robot sees by fitting object detector models to a particular `place'. The key question we seek to answer in this paper is simply: how do we define a place? We build bespoke pedestrian detector models for autonomous driving, highlighting the necessary trade off between generalisation and model capacity as we vary the extent of the `place' we fit to. We demonstrate a sizeable performance gain over a current state-of-the-art detector when using computationally lightweight bespoke place-fitted detector models.