This paper proposes an interaction reasoning network for modelling spatio-temporal relationships between hands and objects in video. The proposed interaction unit utilises a Transformer module to reason about each acting hand, and its spatio-temporal relation to the other hand as well as objects being interacted with. We show that modelling two-handed interactions are critical for action recognition in egocentric video, and demonstrate that by using positionally-encoded trajectories, the network can better recognise observed interactions. We evaluate our proposal on EPIC-KITCHENS and Something-Else datasets, with an ablation study.
Object detection using aerial drone imagery has received a great deal of attention in recent years. While visible light images are adequate for detecting objects in most scenarios, thermal cameras can extend the capabilities of object detection to night-time or occluded objects. As such, RGB and Infrared (IR) fusion methods for object detection are useful and important. One of the biggest challenges in applying deep learning methods to RGB/IR object detection is the lack of available training data for drone IR imagery, especially at night. In this paper, we develop several strategies for creating synthetic IR images using the AIRSim simulation engine and CycleGAN. Furthermore, we utilize an illumination-aware fusion framework to fuse RGB and IR images for object detection on the ground. We characterize and test our methods for both simulated and actual data. Our solution is implemented on an NVIDIA Jetson Xavier running on an actual drone, requiring about 28 milliseconds of processing per RGB/IR image pair.
Effective space traffic management requires positive identification of artificial satellites. Current methods for extracting object identification from observed data require spatially resolved imagery which limits identification to objects in low earth orbits. Most artificial satellites, however, operate in geostationary orbits at distances which prohibit ground based observatories from resolving spatial information. This paper demonstrates an object identification solution leveraging modified residual convolutional neural networks to map distance-invariant spectroscopic data to object identity. We report classification accuracies exceeding 80% for a simulated 64-class satellite problem--even in the case of satellites undergoing constant, random re-orientation. An astronomical observing campaign driven by these results returned accuracies of 72% for a nine-class problem with an average of 100 examples per class, performing as expected from simulation. We demonstrate the application of variational Bayesian inference by dropout, stochastic weight averaging (SWA), and SWA-focused deep ensembling to measure classification uncertainties--critical components in space traffic management where routine decisions risk expensive space assets and carry geopolitical consequences.
Now a days, UAVs such as drones are greatly used for various purposes like that of capturing and target detection from ariel imagery etc. Easy access of these small ariel vehicles to public can cause serious security threats. For instance, critical places may be monitored by spies blended in public using drones. Study in hand proposes an improved and efficient Deep Learning based autonomous system which can detect and track very small drones with great precision. The proposed system consists of a custom deep learning model Tiny YOLOv3, one of the flavors of very fast object detection model You Look Only Once (YOLO) is built and used for detection. The object detection algorithm will efficiently the detect the drones. The proposed architecture has shown significantly better performance as compared to the previous YOLO version. The improvement is observed in the terms of resource usage and time complexity. The performance is measured using the metrics of recall and precision that are 93% and 91% respectively.
Despite the recent success of long-tailed object detection, almost all long-tailed object detectors are developed based on the two-stage paradigm. In practice, one-stage detectors are more prevalent in the industry because they have a simple and fast pipeline that is easy to deploy. However, in the long-tailed scenario, this line of work has not been explored so far. In this paper, we investigate whether one-stage detectors can perform well in this case. We discover the primary obstacle that prevents one-stage detectors from achieving excellent performance is: categories suffer from different degrees of positive-negative imbalance problems under the long-tailed data distribution. The conventional focal loss balances the training process with the same modulating factor for all categories, thus failing to handle the long-tailed problem. To address this issue, we propose the Equalized Focal Loss (EFL) that rebalances the loss contribution of positive and negative samples of different categories independently according to their imbalance degrees. Specifically, EFL adopts a category-relevant modulating factor which can be adjusted dynamically by the training status of different categories. Extensive experiments conducted on the challenging LVIS v1 benchmark demonstrate the effectiveness of our proposed method. With an end-to-end training pipeline, EFL achieves 29.2% in terms of overall AP and obtains significant performance improvements on rare categories, surpassing all existing state-of-the-art methods. The code is available at https://github.com/ModelTC/EOD.
We present a novel method to acquire object representations from online image collections, capturing high-quality geometry and material properties of arbitrary objects from photographs with varying cameras, illumination, and backgrounds. This enables various object-centric rendering applications such as novel-view synthesis, relighting, and harmonized background composition from challenging in-the-wild input. Using a multi-stage approach extending neural radiance fields, we first infer the surface geometry and refine the coarsely estimated initial camera parameters, while leveraging coarse foreground object masks to improve the training efficiency and geometry quality. We also introduce a robust normal estimation technique which eliminates the effect of geometric noise while retaining crucial details. Lastly, we extract surface material properties and ambient illumination, represented in spherical harmonics with extensions that handle transient elements, e.g. sharp shadows. The union of these components results in a highly modular and efficient object acquisition framework. Extensive evaluations and comparisons demonstrate the advantages of our approach in capturing high-quality geometry and appearance properties useful for rendering applications.
Image restoration algorithms such as super resolution (SR) are indispensable pre-processing modules for object detection in degraded images. However, most of these algorithms assume the degradation is fixed and known a priori. When the real degradation is unknown or differs from assumption, both the pre-processing module and the consequent high-level task such as object detection would fail. Here, we propose a novel framework, RestoreDet, to detect objects in degraded low resolution images. RestoreDet utilizes the downsampling degradation as a kind of transformation for self-supervised signals to explore the equivariant representation against various resolutions and other degradation conditions. Specifically, we learn this intrinsic visual structure by encoding and decoding the degradation transformation from a pair of original and randomly degraded images. The framework could further take the advantage of advanced SR architectures with an arbitrary resolution restoring decoder to reconstruct the original correspondence from the degraded input image. Both the representation learning and object detection are optimized jointly in an end-to-end training fashion. RestoreDet is a generic framework that could be implemented on any mainstream object detection architectures. The extensive experiment shows that our framework based on CenterNet has achieved superior performance compared with existing methods when facing variant degradation situations. Our code would be released soon.
Object grounding tasks aim to locate the target object in an image through verbal communications. Understanding human command is an important process needed for effective human-robot communication. However, this is challenging because human commands can be ambiguous and erroneous. This paper aims to disambiguate the human's referring expressions by allowing the agent to ask relevant questions based on semantic data obtained from scene graphs. We test if our agent can use relations between objects from a scene graph to ask semantically relevant questions that can disambiguate the original user command. In this paper, we present Incremental Grounding using Scene Graphs (IGSG), a disambiguation model that uses semantic data from an image scene graph and linguistic structures from a language scene graph to ground objects based on human command. Compared to the baseline, IGSG shows promising results in complex real-world scenes where there are multiple identical target objects. IGSG can effectively disambiguate ambiguous or wrong referring expressions by asking disambiguating questions back to the user.
3D scanning is a complex multistage process that generates a point cloud of an object typically containing damaged parts due to occlusions, reflections, shadows, scanner motion, specific properties of the object surface, imperfect reconstruction algorithms, etc. Point cloud completion is specifically designed to fill in the missing parts of the object and obtain its high-quality 3D representation. The existing completion approaches perform well on the academic datasets with a predefined set of object classes and very specific types of defects; however, their performance drops significantly in the real-world settings and degrades even further on previously unseen object classes. We propose a novel framework that performs well on symmetric objects, which are ubiquitous in man-made environments. Unlike learning-based approaches, the proposed framework does not require training data and is capable of completing non-critical damages occurring in customer 3D scanning process using e.g. Kinect, time-of-flight, or structured light scanners. With thorough experiments, we demonstrate that the proposed framework achieves state-of-the-art efficiency in point cloud completion of real-world customer scans. We benchmark the framework performance on two types of datasets: properly augmented existing academic dataset and the actual 3D scans of various objects.
Modern leading object detectors are either two-stage or one-stage networks repurposed from a deep CNN-based backbone classifier network. YOLOv3 is one such very-well known state-of-the-art one-shot detector that takes in an input image and divides it into an equal-sized grid matrix. The grid cell having the center of an object is the one responsible for detecting the particular object. This paper presents a new mathematical approach that assigns multiple grids per object for accurately tight-fit bounding box prediction. We also propose an effective offline copy-paste data augmentation for object detection. Our proposed method significantly outperforms some current state-of-the-art object detectors with a prospect for further better performance.
We aim to detect and identify multiple objects using multiple cameras and computer vision for disaster response drones. The major challenges are taming detection errors, resolving ID switching and fragmentation, adapting to multi-scale features and multiple views with global camera motion. Two simple approaches are proposed to solve these issues. One is a fast multi-camera system that added a tracklet association, and the other is incorporating a high-performance detector and tracker to resolve restrictions. (...) The accuracy of our first approach (85.71%) is slightly improved compared to our baseline, FairMOT (85.44%) in the validation dataset. In the final results calculated based on L2-norm error, the baseline was 48.1, while the proposed model combination was 34.9, which is a great reduction of error by a margin of 27.4%. In the second approach, although DeepSORT only processes a quarter of all frames due to hardware and time limitations, our model with DeepSORT (42.9%) outperforms FairMOT (71.4%) in terms of recall. Both of our models ranked second and third place in the `AI Grand Challenge' organized by the Korean Ministry of Science and ICT in 2020 and 2021, respectively. The source codes are publicly available at these URLs (github.com/mlvlab/drone_ai_challenge, github.com/mlvlab/Drone_Task1, github.com/mlvlab/Rony2_task3, github.com/mlvlab/Drone_task4).
Communication is defined as the act of sharing or exchanging information, ideas or feelings. To establish communication between two people, both of them are required to have knowledge and understanding of a common language. But in the case of deaf and dumb people, the means of communication are different. Deaf is the inability to hear and dumb is the inability to speak. They communicate using sign language among themselves and with normal people but normal people do not take seriously the importance of sign language. Not everyone possesses the knowledge and understanding of sign language which makes communication difficult between a normal person and a deaf and dumb person. To overcome this barrier, one can build a model based on machine learning. A model can be trained to recognize different gestures of sign language and translate them into English. This will help a lot of people in communicating and conversing with deaf and dumb people. The existing Indian Sing Language Recognition systems are designed using machine learning algorithms with single and double-handed gestures but they are not real-time. In this paper, we propose a method to create an Indian Sign Language dataset using a webcam and then using transfer learning, train a TensorFlow model to create a real-time Sign Language Recognition system. The system achieves a good level of accuracy even with a limited size dataset.
Occlusion between different objects is a typical challenge in Multi-Object Tracking (MOT), which often leads to inferior tracking results due to the missing detected objects. The common practice in multi-object tracking is re-identifying the missed objects after their reappearance. Though tracking performance can be boosted by the re-identification, the annotation of identity is required to train the model. In addition, such practice of re-identification still can not track those highly occluded objects when they are missed by the detector. In this paper, we focus on online multi-object tracking and design two novel modules, the unsupervised re-identification learning module and the occlusion estimation module, to handle these problems. Specifically, the proposed unsupervised re-identification learning module does not require any (pseudo) identity information nor suffer from the scalability issue. The proposed occlusion estimation module tries to predict the locations where occlusions happen, which are used to estimate the positions of missed objects by the detector. Our study shows that, when applied to state-of-the-art MOT methods, the proposed unsupervised re-identification learning is comparable to supervised re-identification learning, and the tracking performance is further improved by the proposed occlusion estimation module.
This work reviews the problem of object detection in underwater environments. We analyse and quantify the shortcomings of conventional state-of-the-art (SOTA) algorithms in the computer vision community when applied to this challenging environment, as well as providing insights and general guidelines for future research efforts. First, we assessed if pretraining with the conventional ImageNet is beneficial when the object detector needs to be applied to environments that may be characterised by a different feature distribution. We then investigate whether two-stage detectors yields to better performance with respect to single-stage detectors, in terms of accuracy, intersection of union (IoU), floating operation per second (FLOPS), and inference time. Finally, we assessed the generalisation capability of each model to a lower quality dataset to simulate performance on a real scenario, in which harsher conditions ought to be expected. Our experimental results provide evidence that underwater object detection requires searching for "ad-hoc" architectures than merely training SOTA architectures on new data, and that pretraining is not beneficial.
We propose a 3-D material style transfer framework for reconstructing invisible (or faded) appearance properties in complex natural materials. Our algorithm addresses the technical challenge of transferring appearance properties from one object to another of the same material when both objects have intricate, noncorresponding color patterns. Eggshells, exoskeletons, and minerals, for example, have patterns composed of highly randomized layers of organic and inorganic compounds. These materials pose a challenge as the distribution of compounds that determine surface color changes from object to object and within local pattern regions. Our solution adapts appearance observations from a material property distribution in an exemplar to the material property distribution of a target object to reconstruct its unknown appearance. We use measured reflectance in 3-D bispectral textures to record changing material property distributions. Our novel implementation of spherical harmonics uses principles from chemistry and biology to learn relationships between color (hue and saturation) and material composition and concentration in an exemplar. The encoded relationships are transformed to the property distribution of a target for color recovery and material assignment. Quantitative and qualitative evaluation methods show that we replicate color patterns more accurately than methods that only rely on shape correspondences and coarse-level perceptual differences. We demonstrate applications of our work for reconstructing color in extinct fossils, restoring faded artifacts and generating synthetic textures.
Bounding-box annotation form has been the most frequently used method for visual object localization tasks. However, bounding-box annotation relies on a large amount of precisely annotating bounding boxes, and it is expensive and laborious. It is impossible to be employed in practical scenarios and even redundant for some applications (such as tiny person localization) that the size would not matter. Therefore, we propose a novel point-based framework for the person localization task by annotating each person as a coarse point (CoarsePoint) instead of an accurate bounding box that can be any point within the object extent. Then, the network predicts the person's location as a 2D coordinate in the image. Although this greatly simplifies the data annotation pipeline, the CoarsePoint annotation inevitably decreases label reliability (label uncertainty) and causes network confusion during training. As a result, we propose a point self-refinement approach that iteratively updates point annotations in a self-paced way. The proposed refinement system alleviates the label uncertainty and progressively improves localization performance. Experimental results show that our approach has achieved comparable object localization performance while saving up to 80$\%$ of annotation cost.
The concept of geo-localization refers to the process of determining where on earth some `entity' is located, typically using Global Positioning System (GPS) coordinates. The entity of interest may be an image, sequence of images, a video, satellite image, or even objects visible within the image. As massive datasets of GPS tagged media have rapidly become available due to smartphones and the internet, and deep learning has risen to enhance the performance capabilities of machine learning models, the fields of visual and object geo-localization have emerged due to its significant impact on a wide range of applications such as augmented reality, robotics, self-driving vehicles, road maintenance, and 3D reconstruction. This paper provides a comprehensive survey of geo-localization involving images, which involves either determining from where an image has been captured (Image geo-localization) or geo-locating objects within an image (Object geo-localization). We will provide an in-depth study, including a summary of popular algorithms, a description of proposed datasets, and an analysis of performance results to illustrate the current state of each field.
We present a dataset that contains object annotations with unique object identities (IDs) for the High Efficiency Video Coding (HEVC) v1 Common Test Conditions (CTC) sequences. Ground-truth annotations for 13 sequences were prepared and released as the dataset called SFU-HW-Tracks-v1. For each video frame, ground truth annotations include object class ID, object ID, and bounding box location and its dimensions. The dataset can be used to evaluate object tracking performance on uncompressed video sequences and study the relationship between video compression and object tracking.
Weakly supervised object localization (WSOL) is a challenging task to localize the object by only category labels. However, there is contradiction between classification and localization because accurate classification network tends to pay attention to discriminative region of objects rather than the entirety. We propose this discrimination is caused by handcraft threshold choosing in CAM-based methods. Therefore, we propose Clustering and Filter of Tokens (CaFT) with Vision Transformer (ViT) backbone to solve this problem in another way. CaFT first sends the patch tokens of the image split to ViT and cluster the output tokens to generate initial mask of the object. Secondly, CaFT considers the initial mask as pseudo labels to train a shallow convolution head (Attention Filter, AtF) following backbone to directly extract the mask from tokens. Then, CaFT splits the image into parts, outputs masks respectively and merges them into one refined mask. Finally, a new AtF is trained on the refined masks and used to predict the box of object. Experiments verify that CaFT outperforms previous work and achieves 97.55\% and 69.86\% localization accuracy with ground-truth class on CUB-200 and ImageNet-1K respectively. CaFT provides a fresh way to think about the WSOL task.
Open World Object Detection (OWOD), simulating the real dynamic world where knowledge grows continuously, attempts to detect both known and unknown classes and incrementally learn the identified unknown ones. We find that although the only previous OWOD work constructively puts forward to the OWOD definition, the experimental settings are unreasonable with the illogical benchmark, confusing metric calculation, and inappropriate method. In this paper, we rethink the OWOD experimental setting and propose five fundamental benchmark principles to guide the OWOD benchmark construction. Moreover, we design two fair evaluation protocols specific to the OWOD problem, filling the void of evaluating from the perspective of unknown classes. Furthermore, we introduce a novel and effective OWOD framework containing an auxiliary Proposal ADvisor (PAD) and a Class-specific Expelling Classifier (CEC). The non-parametric PAD could assist the RPN in identifying accurate unknown proposals without supervision, while CEC calibrates the over-confident activation boundary and filters out confusing predictions through a class-specific expelling function. Comprehensive experiments conducted on our fair benchmark demonstrate that our method outperforms other state-of-the-art object detection approaches in terms of both existing and our new metrics. Our benchmark and code are available at https://github.com/RE-OWOD/RE-OWOD.