Combining multiple complementary techniques together has long been regarded as a way to improve performance. In visual localization, multi-sensor fusion, multi-process fusion of a single sensing modality, and even combinations of different localization techniques have been shown to result in improved performance. However, merely fusing together different localization techniques does not account for the varying performance characteristics of different localization techniques. In this paper we present a novel, hierarchical localization system that explicitly benefits from three varying characteristics of localization techniques: the distribution of their localization hypotheses, their appearance- and viewpoint-invariant properties, and the resulting differences in where in an environment each system works well and fails. We show how two techniques deployed hierarchically work better than in parallel fusion, how combining two different techniques works better than two levels of a single technique, even when the single technique has superior individual performance, and develop two and three-tier hierarchical structures that progressively improve localization performance. Finally, we develop a stacked hierarchical framework where localization hypotheses from techniques with complementary characteristics are concatenated at each layer, significantly improving retention of the correct hypothesis through to the final localization stage. Using two challenging datasets, we show the proposed system outperforming state-of-the-art techniques.
Visual place recognition algorithms trade off three key characteristics: their storage footprint, their computational requirements, and their resultant performance, often expressed in terms of recall rate. Significant prior work has investigated highly compact place representations, sub-linear computational scaling and sub-linear storage scaling techniques, but have always involved a significant compromise in one or more of these regards, and have only been demonstrated on relatively small datasets. In this paper we present a novel place recognition system which enables for the first time the combination of ultra-compact place representations, near sub-linear storage scaling and extremely lightweight compute requirements. Our approach exploits the inherently sequential nature of much spatial data in the robotics domain and inverts the typical target criteria, through intentionally coarse scalar quantization-based hashing that leads to more collisions but is resolved by sequence-based matching. For the first time, we show how effective place recognition rates can be achieved on a new very large 10 million place dataset, requiring only 8 bytes of storage per place and 37K unitary operations to achieve over 50% recall for matching a sequence of 100 frames, where a conventional state-of-the-art approach both consumes 1300 times more compute and fails catastrophically. We present analysis investigating the effectiveness of our hashing overload approach under varying sizes of quantized vector length, comparison of near miss matches with the actual match selections and characterise the effect of variance re-scaling of data on quantization.
State-of-the-art algorithms for visual place recognition can be broadly split into two categories: computationally expensive deep-learning/image retrieval based techniques with minimal biological plausibility, and computationally cheap, biologically inspired models that yield poor performance in real-world environments. In this paper we present a new compact and high-performing system that bridges this divide for the first time. Our approach comprises two key components: FlyNet, a compact, sparse two-layer neural network inspired by fruit fly brain architectures, and a one-dimensional continuous attractor neural network (CANN). Our FlyNet+CANN network combines the compact pattern recognition capabilities of the FlyNet model with the powerful temporal filtering capabilities of an equally compact CANN, replicating entirely in a neural network implementation the functionality that yields high performance in algorithmic localization approaches like SeqSLAM. We evaluate our approach and compare it to three state-of-the-art methods on two benchmark real-world datasets with small viewpoint changes and extreme appearance variations including different times of day (afternoon to night) where it achieves an AUC performance of 87%, compared to 60% for Multi-Process Fusion, 46% for LoST-X and 1% for SeqSLAM, while being 6.5, 310, and 1.5 times faster respectively.
Visual navigation tasks in real world environments often require both self-motion and place recognition feedback. While deep reinforcement learning has shown success in solving these perception and decision-making problems in an end-to-end manner, these algorithms require large amounts of experience to learn navigation policies from high-dimensional inputs, which is generally impractical for real robots due to sample complexity. In this paper, we address these problems with two main contributions. We first leverage place recognition and deep learning techniques combined with goal destination feedback to generate compact, bimodal images representations that can then be used to effectively learn control policies at kilometer scale from a small amount of experience. Second, we present an interactive and realistic framework, called CityLearn, that enables for the first time the training of navigation algorithms across city-sized, real-world environments with extreme environmental changes. CityLearn features over 10 benchmark real-world datasets often used in place recognition research with more than 100 recorded traversals and across 60 cities around the world. We evaluate our approach in two CityLearn environments where our navigation policy is trained using a single traversal. Results show our method can be over 2 orders of magnitude faster than when using raw images and can also generalize across extreme visual changes including day to night and summer to winter transitions.
In this work we focus on improving the efficiency and generalisation of learned navigation strategies when transferred from its training environment to previously unseen ones. We present an extension of the residual reinforcement learning framework from the robotic manipulation literature and adapt it to the vast and unstructured environments that mobile robots can operate in. The concept is based on learning a residual control effect to add to a typical sub-optimal classical controller in order to close the performance gap, whilst guiding the exploration process during training for improved data efficiency. We exploit this tight coupling and propose a novel deployment strategy, switching Residual Reactive Navigation (sRNN), which yields efficient trajectories whilst probabilistically switching to a classical controller in cases of high policy uncertainty. Our approach achieves improved performance over end-to-end alternatives and can be incorporated as part of a complete navigation stack for cluttered indoor navigation tasks in the real world. The code and training environment for this project is made publicly available at https://github.com/krishanrana/2D_SRRN.
In the last few years, Deep Convolutional Neural Networks (D-CNNs) have shown state-of-the-art performances for Visual Place Recognition (VPR). Their prestigious generalization power has played a vital role in identifying persistent image regions under changing conditions and viewpoints. However, against the computation intensive D-CNNs based VPR algorithms, lightweight VPR techniques are preferred for resource-constraints mobile robots. This paper presents a lightweight CNN-based VPR technique that captures multi-layer context-aware attentions robust under changing environment and viewpoints. Evaluation of challenging benchmark datasets reveals better performance at low memory and resources utilization over state-of-the-art contemporary VPR methodologies.
Visual Place Recognition (VPR) is a fundamental yet challenging task for small Unmanned Aerial Vehicle (UAV). The core reasons are the extreme viewpoint changes, and limited computational power onboard a UAV which restricts the applicability of robust but computation intensive state-of-the-art VPR methods. In this context, a viable approach is to use local image descriptors for performing VPR as these can be computed relatively efficiently without the need of any special hardware, such as a GPU. However, the choice of a local feature descriptor is not trivial and calls for a detailed investigation as there is a trade-off between VPR accuracy and the required computational effort. To fill this research gap, this paper examines the performance of several state-of-the-art local feature descriptors, both from accuracy and computational perspectives, specifically for VPR application utilizing standard aerial datasets. The presented results confirm that a trade-off between accuracy and computational effort is inevitable while executing VPR on resource-constrained hardware.
Visual localization algorithms have achieved significant improvements in performance thanks to recent advances in camera technology and vision-based techniques. However, there remains one critical caveat: all current approaches that are based on image retrieval currently scale at best linearly with the size of the environment with respect to both storage, and consequentially in most approaches, query time. This limitation severely curtails the capability of autonomous systems in a wide range of compute, power, storage, size, weight or cost constrained applications such as drones. In this work, we present a novel binary tree encoding approach for visual localization which can serve as an alternative for existing quantization and indexing techniques. The proposed tree structure allows us to derive a compressed training scheme that achieves sub-linearity in both required storage and inference time. The encoding memory can be easily configured to satisfy different storage constraints. Moreover, our approach is amenable to an optional sequence filtering mechanism to further improve the localization results, while maintaining the same amount of storage. Our system is entirely agnostic to the front-end descriptors, allowing it to be used on top of recent state-of-the-art image representations. Experimental results show that the proposed method significantly outperforms state-of-the-art approaches under limited storage constraints.
Localization is a critical capability for robots, drones and autonomous vehicles operating in a wide range of environments. One of the critical considerations for designing, training or calibrating visual localization systems is the coverage of the visual sensors equipped on the platforms. In an aerial context for example, the altitude of the platform and camera field of view plays a critical role in how much of the environment a downward facing camera can perceive at any one time. Furthermore, in other applications, such as on roads or in indoor environments, additional factors such as camera resolution and sensor placement altitude can also affect this coverage. The sensor coverage and the subsequent processing of its data also has significant computational implications. In this paper we present for the first time a set of methods for automatically determining the trade-off between coverage and visual localization performance, enabling the identification of the minimum visual sensor coverage required to obtain optimal localization performance with minimal compute. We develop a localization performance indicator based on the overlapping coefficient, and demonstrate its predictive power for localization performance with a certain sensor coverage. We evaluate our method on several challenging real-world datasets from aerial and ground-based domains, and demonstrate that our method is able to automatically optimize for coverage using a small amount of calibration data. We hope these results will assist in the design of localization systems for future autonomous robot, vehicle and flying systems.
CNNs have excelled at performing place recognition over time, particularly when the neural network is optimized for localization in the current environmental conditions. In this paper we investigate the concept of feature map filtering, where, rather than using all the activations within a convolutional tensor, only the most useful activations are used. Since specific feature maps encode different visual features, the objective is to remove feature maps that are detract from the ability to recognize a location across appearance changes. Our key innovation is to filter the feature maps in an early convolutional layer, but then continue to run the network and extract a feature vector using a later layer in the same network. By filtering early visual features and extracting a feature vector from a higher, more viewpoint invariant later layer, we demonstrate improved condition and viewpoint invariance. Our approach requires image pairs for training from the deployment environment, but we show that state-of-the-art performance can regularly be achieved with as little as a single training image pair. An exhaustive experimental analysis is performed to determine the full scope of causality between early layer filtering and late layer extraction. For validity, we use three datasets: Oxford RobotCar, Nordland, and Gardens Point, achieving overall superior performance to NetVLAD. The work provides a number of new avenues for exploring CNN optimizations, without full re-training.