Street-level imagery holds a significant potential to scale-up in-situ data collection. This is enabled by combining the use of cheap high quality cameras with recent advances in deep learning compute solutions to derive relevant thematic information. We present a framework to collect and extract crop type and phenological information from street level imagery using computer vision. During the 2018 growing season, high definition pictures were captured with side-looking action cameras in the Flevoland province of the Netherlands. Each month from March to October, a fixed 200-km route was surveyed collecting one picture per second resulting in a total of 400,000 geo-tagged pictures. At 220 specific parcel locations detailed on the spot crop phenology observations were recorded for 17 crop types. Furthermore, the time span included specific pre-emergence parcel stages, such as differently cultivated bare soil for spring and summer crops as well as post-harvest cultivation practices, e.g. green manuring and catch crops. Classification was done using TensorFlow with a well-known image recognition model, based on transfer learning with convolutional neural networks (MobileNet). A hypertuning methodology was developed to obtain the best performing model among 160 models. This best model was applied on an independent inference set discriminating crop type with a Macro F1 score of 88.1% and main phenological stage at 86.9% at the parcel level. Potential and caveats of the approach along with practical considerations for implementation and improvement are discussed. The proposed framework speeds up high quality in-situ data collection and suggests avenues for massive data collection via automated classification using computer vision.
Unpaired video-to-video translation aims to translate videos between a source and a target domain without the need of paired training data, making it more feasible for real applications. Unfortunately, the translated videos generally suffer from temporal and semantic inconsistency. To address this, many existing works adopt spatiotemporal consistency constraints incorporating temporal information based on motion estimation. However, the inaccuracies in the estimation of motion deteriorate the quality of the guidance towards spatiotemporal consistency, which leads to unstable translation. In this work, we propose a novel paradigm that regularizes the spatiotemporal consistency by synthesizing motions in input videos with the generated optical flow instead of estimating them. Therefore, the synthetic motion can be applied in the regularization paradigm to keep motions consistent across domains without the risk of errors in motion estimation. Thereafter, we utilize our unsupervised recycle and unsupervised spatial loss, guided by the pseudo-supervision provided by the synthetic optical flow, to accurately enforce spatiotemporal consistency in both domains. Experiments show that our method is versatile in various scenarios and achieves state-of-the-art performance in generating temporally and semantically consistent videos. Code is available at: https://github.com/wangkaihong/Unsup_Recycle_GAN/.
We propose an accurate and robust multi-modal sensor fusion framework, MetroLoc, towards one of the most extreme scenarios, the large-scale metro vehicle localization and mapping. MetroLoc is built atop an IMU-centric state estimator that tightly couples light detection and ranging (LiDAR), visual, and inertial information with the convenience of loosely coupled methods. The proposed framework is composed of three submodules: IMU odometry, LiDAR-inertial odometry (LIO), and Visual-inertial odometry (VIO). The IMU is treated as the primary sensor, which achieves the observations from LIO and VIO to constrain the accelerometer and gyroscope biases. Compared to previous point-only LIO methods, our approach leverages more geometry information by introducing both line and plane features into motion estimation. The VIO also utilizes the environmental structure information by employing both lines and points. Our proposed method has been extensively tested in the long-during metro environments with a maintenance vehicle. Experimental results show the system more accurate and robust than the state-of-the-art approaches with real-time performance. Besides, we develop a series of Virtual Reality (VR) applications towards efficient, economical, and interactive rail vehicle state and trackside infrastructure monitoring, which has already been deployed to an outdoor testing railroad.
This report proposes a combined optimal control and perception framework for Micro Aerial Vehicle (MAV) autonomous navigation in novel indoor enclosed environments, relying exclusively on on-board sensor data. We use privileged information from a simulator to generate optimal waypoints in 3D space for our perception system learns to imitate. The trained learning based perception module in turn is able to generate similar obstacle avoiding waypoints from sensor data (RGB + IMU) alone. We demonstrate the efficacy of the framework across novel scenes in the iGibson simulation environment.
Existing deep learning-based video super-resolution (SR) methods usually depend on the supervised learning approach, where the training data is usually generated by the blurring operation with known or predefined kernels (e.g., Bicubic kernel) followed by a decimation operation. However, this does not hold for real applications as the degradation process is complex and cannot be approximated by these idea cases well. Moreover, obtaining high-resolution (HR) videos and the corresponding low-resolution (LR) ones in real-world scenarios is difficult. To overcome these problems, we propose a self-supervised learning method to solve the blind video SR problem, which simultaneously estimates blur kernels and HR videos from the LR videos. As directly using LR videos as supervision usually leads to trivial solutions, we develop a simple and effective method to generate auxiliary paired data from original LR videos according to the image formation of video SR, so that the networks can be better constrained by the generated paired data for both blur kernel estimation and latent HR video restoration. In addition, we introduce an optical flow estimation module to exploit the information from adjacent frames for HR video restoration. Experiments show that our method performs favorably against state-of-the-art ones on benchmarks and real-world videos.
In this paper, we propose a simple attention mechanism, we call Box-Attention. It enables spatial interaction between grid features, as sampled from boxes of interest, and improves the learning capability of transformers for several vision tasks. Specifically, we present BoxeR, short for Box Transformer, which attends to a set of boxes by predicting their transformation from a reference window on an input feature map. The BoxeR computes attention weights on these boxes by considering its grid structure. Notably, BoxeR-2D naturally reasons about box information within its attention module, making it suitable for end-to-end instance detection and segmentation tasks. By learning invariance to rotation in the box-attention module, BoxeR-3D is capable of generating discriminative information from a bird-eye-view plane for 3D end-to-end object detection. Our experiments demonstrate that the proposed BoxeR-2D achieves better results on COCO detection, and reaches comparable performance with well-established and highly-optimized Mask R-CNN on COCO instance segmentation. BoxeR-3D already obtains a compelling performance for the vehicle category of Waymo Open, without any class-specific optimization. The code will be released.
Image inpainting is an effective method to enhance distorted digital images. Different inpainting methods use the information of neighboring pixels to predict the value of missing pixels. Recently deep neural networks have been used to learn structural and semantic details of images for inpainting purposes. In this paper, we propose a network for image inpainting. This network, similar to U-Net, extracts various features from images, leading to better results. We improved the final results by replacing the damaged pixels with the recovered pixels of the output images. Our experimental results show that this method produces high-quality results compare to the traditional methods.
How do neural network image classifiers respond to simpler and simpler inputs? And what do such responses reveal about the learning process? To answer these questions, we need a clear measure of input simplicity (or inversely, complexity), an optimization objective that correlates with simplification, and a framework to incorporate such objective into training and inference. Lastly we need a variety of testbeds to experiment and evaluate the impact of such simplification on learning. In this work, we measure simplicity with the encoding bit size given by a pretrained generative model, and minimize the bit size to simplify inputs in training and inference. We investigate the effect of such simplification in several scenarios: conventional training, dataset condensation and post-hoc explanations. In all settings, inputs are simplified along with the original classification task, and we investigate the trade-off between input simplicity and task performance. For images with injected distractors, such simplification naturally removes superfluous information. For dataset condensation, we find that inputs can be simplified with almost no accuracy degradation. When used in post-hoc explanation, our learning-based simplification approach offers a valuable new tool to explore the basis of network decisions.
Recently, attention-based encoder-decoder models have been used extensively in image captioning. Yet there is still great difficulty for the current methods to achieve deep image understanding. In this work, we argue that such understanding requires visual attention to correlated image regions and semantic attention to coherent attributes of interest. To perform effective attention, we explore image captioning from a cross-modal perspective and propose the Global-and-Local Information Exploring-and-Distilling approach that explores and distills the source information in vision and language. It globally provides the aspect vector, a spatial and relational representation of images based on caption contexts, through the extraction of salient region groupings and attribute collocations, and locally extracts the fine-grained regions and attributes in reference to the aspect vector for word selection. Our fully-attentive model achieves a CIDEr score of 129.3 in offline COCO evaluation on the COCO testing set with remarkable efficiency in terms of accuracy, speed, and parameter budget.
Melody extraction is a vital music information retrieval task among music researchers for its potential applications in education pedagogy and the music industry. Melody extraction is a notoriously challenging task due to the presence of background instruments. Also, often melodic source exhibits similar characteristics to that of the other instruments. The interfering background accompaniment with the vocals makes extracting the melody from the mixture signal much more challenging. Until recently, classical signal processing-based melody extraction methods were quite popular among melody extraction researchers. The ability of the deep learning models to model large-scale data and the ability of the models to learn automatic features by exploiting spatial and temporal dependencies inspired many researchers to adopt deep learning models for melody extraction. In this paper, an attempt has been made to review the up-to-date data-driven deep learning approaches for melody extraction from polyphonic music. The available deep models have been categorized based on the type of neural network used and the output representation they use for predicting melody. Further, the architectures of the 25 melody extraction models are briefly presented. The loss functions used to optimize the model parameters of the melody extraction models are broadly categorized into four categories and briefly describe the loss functions used by various melody extraction models. Also, the various input representations adopted by the melody extraction models and the parameter settings are deeply described. A section describing the explainability of the block-box melody extraction deep neural networks is included. The performance of 25 melody extraction methods is compared. The possible future directions to explore/improve the melody extraction methods are also presented in the paper.