Object detection in videos is an important task in computer vision for various applications such as object tracking, video summarization and video search. Although great progress has been made in improving the accuracy of object detection in recent years due to the rise of deep neural networks, the state-of-the-art algorithms are highly computationally intensive. In order to address this challenge, we make two important observations in the context of videos: (i) Objects often occupy only a small fraction of the area in each video frame, and (ii) There is a high likelihood of strong temporal correlation between consecutive frames. Based on these observations, we propose Pack and Detect (PaD), an approach to reduce the computational requirements of object detection in videos. In PaD, only selected video frames called anchor frames are processed at full size. In the frames that lie between anchor frames (inter-anchor frames), regions of interest (ROIs) are identified based on the detections in the previous frame. We propose an algorithm to pack the ROIs of each inter-anchor frame together into a reduced-size frame. The computational requirements of the detector are reduced due to the lower size of the input. In order to maintain the accuracy of object detection, the proposed algorithm expands the ROIs greedily to provide additional background around each object to the detector. PaD can use any underlying neural network architecture to process the full-size and reduced-size frames. Experiments using the ImageNet video object detection dataset indicate that PaD can potentially reduce the number of FLOPS required for a frame by $4\times$. This leads to an overall increase in throughput of $1.25\times$ on a 2.1 GHz Intel Xeon server with a NVIDIA Titan X GPU at the cost of $1.1\%$ drop in accuracy.
Object detection in three-dimensional (3D) space attracts much interest from academia and industry since it is an essential task in AI-driven applications such as robotics, autonomous driving, and augmented reality. As the basic format of 3D data, the point cloud can provide detailed geometric information about the objects in the original 3D space. However, due to 3D data's sparsity and unorderedness, specially designed networks and modules are needed to process this type of data. Attention mechanism has achieved impressive performance in diverse computer vision tasks; however, it is unclear how attention modules would affect the performance of 3D point cloud object detection and what sort of attention modules could fit with the inherent properties of 3D data. This work investigates the role of the attention mechanism in 3D point cloud object detection and provides insights into the potential of different attention modules. To achieve that, we comprehensively investigate classical 2D attentions, novel 3D attentions, including the latest point cloud transformers on SUN RGB-D and ScanNetV2 datasets. Based on the detailed experiments and analysis, we conclude the effects of different attention modules. This paper is expected to serve as a reference source for benefiting attention-embedded 3D point cloud object detection. The code and trained models are available at: https://github.com/ShiQiu0419/attentions_in_3D_detection.
With the growth of digitized comics, image understanding techniques are becoming important. In this paper, we focus on object detection, which is a fundamental task of image understanding. Although convolutional neural networks (CNN)-based methods archived good performance in object detection for naturalistic images, there are two problems in applying these methods to the comic object detection task. First, there is no large-scale annotated comics dataset. The CNN-based methods require large-scale annotations for training. Secondly, the objects in comics are highly overlapped compared to naturalistic images. This overlap causes the assignment problem in the existing CNN-based methods. To solve these problems, we proposed a new annotation dataset and a new CNN model. We annotated an existing image dataset of comics and created the largest annotation dataset, named Manga109-annotations. For the assignment problem, we proposed a new CNN-based detector, SSD300-fork. We compared SSD300-fork with other detection methods using Manga109-annotations and confirmed that our model outperformed them based on the mAP score.
Precisely detection of Unmanned Aerial Vehicles(UAVs) plays a critical role in UAV defense systems. Deep learning is widely adopted for UAV object detection whereas researches on this topic are limited by the amount of dataset and small scale of UAV. To tackle these problems, a novel comprehensive approach that combines transfer learning based on simulation data and adaptive fusion is proposed. Firstly, the open-source plugin AirSim proposed by Microsoft is used to generate mass realistic simulation data. Secondly, transfer learning is applied to obtain a pre-trained YOLOv5 model on the simulated dataset and fine-tuned model on the real-world dataset. Finally, an adaptive fusion mechanism is proposed to further improve small object detection performance. Experiment results demonstrate the effectiveness of simulation-based transfer learning which leads to a 2.7% performance increase on UAV object detection. Furthermore, with transfer learning and adaptive fusion mechanism, 7.1% improvement is achieved compared to the original YOLO v5 model.
The prior self-supervised learning researches mainly select image-level instance discrimination as pretext task. It achieves a fantastic classification performance that is comparable to supervised learning methods. However, with degraded transfer performance on downstream tasks such as object detection. To bridge the performance gap, we propose a novel object-level self-supervised learning method, called Contrastive learning with Downstream background invariance (CoDo). The pretext task is converted to focus on instance location modeling for various backgrounds, especially for downstream datasets. The ability of background invariance is considered vital for object detection. Firstly, a data augmentation strategy is proposed to paste the instances onto background images, and then jitter the bounding box to involve background information. Secondly, we implement architecture alignment between our pretraining network and the mainstream detection pipelines. Thirdly, hierarchical and multi views contrastive learning is designed to improve performance of visual representation learning. Experiments on MSCOCO demonstrate that the proposed CoDo with common backbones, ResNet50-FPN, yields strong transfer learning results for object detection.
Recently, three-dimensional (3D) detection based on stereo images has progressed remarkably; however, most advanced methods adopt anchor-based two-dimensional (2D) detection or depth estimation to address this problem. Nevertheless, high computational cost inhibits these methods from achieving real-time performance. In this study, we propose a 3D object detection method, Stereo CenterNet (SC), using geometric information in stereo imagery. SC predicts the four semantic key points of the 3D bounding box of the object in space and utilizes 2D left and right boxes, 3D dimension, orientation, and key points to restore the bounding box of the object in the 3D space. Subsequently, we adopt an improved photometric alignment module to further optimize the position of the 3D bounding box. Experiments conducted on the KITTI dataset indicate that the proposed SC exhibits the best speed-accuracy trade-off among advanced methods without using extra data.
We introduce Few-Shot Video Object Detection (FSVOD) with three contributions to real-world visual learning challenge in our highly diverse and dynamic world: 1) a large-scale video dataset FSVOD-500 comprising of 500 classes with class-balanced videos in each category for few-shot learning; 2) a novel Tube Proposal Network (TPN) to generate high-quality video tube proposals for aggregating feature representation for the target video object which can be highly dynamic; 3) a strategically improved Temporal Matching Network (TMN+) for matching representative query tube features with better discriminative ability thus achieving higher diversity. Our TPN and TMN+ are jointly and end-to-end trained. Extensive experiments demonstrate that our method produces significantly better detection results on two few-shot video object detection datasets compared to image-based methods and other naive video-based extensions. Codes and datasets are released at \url{https://github.com/fanq15/FewX}.
Existing domain adaptation (DA) and generalization (DG) methods in object detection enforce feature alignment in the visual space but face challenges like object appearance variability and scene complexity, which make it difficult to distinguish between objects and achieve accurate detection. In this paper, we are the first to address the problem of semi-supervised domain generalization by exploring vision-language pre-training and enforcing feature alignment through the language space. We employ a novel Cross-Domain Descriptive Multi-Scale Learning (CDDMSL) aiming to maximize the agreement between descriptions of an image presented with different domain-specific characteristics in the embedding space. CDDMSL significantly outperforms existing methods, achieving 11.7% and 7.5% improvement in DG and DA settings, respectively. Comprehensive analysis and ablation studies confirm the effectiveness of our method, positioning CDDMSL as a promising approach for domain generalization in object detection tasks.
Humans have a remarkable ability to perceive and reason about the world around them by understanding the relationships between objects. In this paper, we investigate the effectiveness of using such relationships for object detection and instance segmentation. To this end, we propose a Relational Prior-based Feature Enhancement Model (RP-FEM), a graph transformer that enhances object proposal features using relational priors. The proposed architecture operates on top of scene graphs obtained from initial proposals and aims to concurrently learn relational context modeling for object detection and instance segmentation. Experimental evaluations on COCO show that the utilization of scene graphs, augmented with relational priors, offer benefits for object detection and instance segmentation. RP-FEM demonstrates its capacity to suppress improbable class predictions within the image while also preventing the model from generating duplicate predictions, leading to improvements over the baseline model on which it is built.
Deep neural network based object detection hasbecome the cornerstone of many real-world applications. Alongwith this success comes concerns about its vulnerability tomalicious attacks. To gain more insight into this issue, we proposea contextual camouflage attack (CCA for short) algorithm to in-fluence the performance of object detectors. In this paper, we usean evolutionary search strategy and adversarial machine learningin interactions with a photo-realistic simulated environment tofind camouflage patterns that are effective over a huge varietyof object locations, camera poses, and lighting conditions. Theproposed camouflages are validated effective to most of the state-of-the-art object detectors.
We present a survey on maritime object detection and tracking approaches, which are essential for the development of a navigational system for autonomous ships. The electro-optical (EO) sensor considered here is a video camera that operates in the visible or the infrared spectra, which conventionally complement radar and sonar and have demonstrated effectiveness for situational awareness at sea has demonstrated its effectiveness over the last few years. This paper provides a comprehensive overview of various approaches of video processing for object detection and tracking in the maritime environment. We follow an approach-based taxonomy wherein the advantages and limitations of each approach are compared. The object detection system consists of the following modules: horizon detection, static background subtraction and foreground segmentation. Each of these has been studied extensively in maritime situations and has been shown to be challenging due to the presence of background motion especially due to waves and wakes. The main processes involved in object tracking include video frame registration, dynamic background subtraction, and the object tracking algorithm itself. The challenges for robust tracking arise due to camera motion, dynamic background and low contrast of tracked object, possibly due to environmental degradation. The survey also discusses multisensor approaches and commercial maritime systems that use EO sensors. The survey also highlights methods from computer vision research which hold promise to perform well in maritime EO data processing. Performance of several maritime and computer vision techniques is evaluated on newly proposed Singapore Maritime Dataset.
The better accuracy and efficiency trade-off has been a challenging problem in object detection. In this work, we are dedicated to studying key optimizations and neural network architecture choices for object detection to improve accuracy and efficiency. We investigate the applicability of the anchor-free strategy on lightweight object detection models. We enhance the backbone structure and design the lightweight structure of the neck, which improves the feature extraction ability of the network. We improve label assignment strategy and loss function to make training more stable and efficient. Through these optimizations, we create a new family of real-time object detectors, named PP-PicoDet, which achieves superior performance on object detection for mobile devices. Our models achieve better trade-offs between accuracy and latency compared to other popular models. PicoDet-S with only 0.99M parameters achieves 30.6% mAP, which is an absolute 4.8% improvement in mAP while reducing mobile CPU inference latency by 55% compared to YOLOX-Nano, and is an absolute 7.1% improvement in mAP compared to NanoDet. It reaches 123 FPS (150 FPS using Paddle Lite) on mobile ARM CPU when the input size is 320. PicoDet-L with only 3.3M parameters achieves 40.9% mAP, which is an absolute 3.7% improvement in mAP and 44% faster than YOLOv5s. As shown in Figure 1, our models far outperform the state-of-the-art results for lightweight object detection. Code and pre-trained models are available at https://github.com/PaddlePaddle/PaddleDetection.
We present an approach for object segmentation in videos that combines frame-level object detection with concepts from object tracking and motion segmentation. The approach extracts temporally consistent object tubes based on an off-the-shelf detector. Besides the class label for each tube, this provides a location prior that is independent of motion. For the final video segmentation, we combine this information with motion cues. The method overcomes the typical problems of weakly supervised/unsupervised video segmentation, such as scenes with no motion, dominant camera motion, and objects that move as a unit. In contrast to most tracking methods, it provides an accurate, temporally consistent segmentation of each object. We report results on four video segmentation datasets: YouTube Objects, SegTrackv2, egoMotion, and FBMS.
Object detection and data association are critical components in multi-object tracking (MOT) systems. Despite the fact that the two components are dependent on each other, prior works often design detection and data association modules separately which are trained with separate objectives. As a result, one cannot back-propagate the gradients and optimize the entire MOT system, which leads to sub-optimal performance. To address this issue, recent works simultaneously optimize detection and data association modules under a joint MOT framework, which has shown improved performance in both modules. In this work, we propose a new instance of joint MOT approach based on Graph Neural Networks (GNNs). The key idea is that GNNs can model relations between variable-sized objects in both the spatial and temporal domains, which is essential for learning discriminative features for detection and data association. Through extensive experiments on the MOT15/16/17/20 datasets, we demonstrate the effectiveness of our GNN-based joint MOT approach and show state-of-the-art performance for both detection and MOT tasks. Our code is available at: https://github.com/yongxinw/GSDT
In this report, we describe the technical details of oursubmission to the EPIC-Kitchens Object Detection Challenge.Duck filling and mix-up techniques are firstly introduced to augment the data and significantly improve the robustness of the proposed method. Then we propose GRE-FPN and Hard IoU-imbalance Sampler methods to extract more representative global object features. To bridge the gap of category imbalance, Class Balance Sampling is utilized and greatly improves the test results. Besides, some training and testing strategies are also exploited, such as Stochastic Weight Averaging and multi-scale testing. Experimental results demonstrate that our approach can significantly improve the mean Average Precision (mAP) of object detection on both the seen and unseen test sets of EPICKitchens.
DEtection TRansformer (DETR) for object detection reaches competitive performance compared with Faster R-CNN via a transformer encoder-decoder architecture. However, trained with scratch transformers, DETR needs large-scale training data and an extreme long training schedule even on COCO dataset. Inspired by the great success of pre-training transformers in natural language processing, we propose a novel pretext task named random query patch detection in Unsupervised Pre-training DETR (UP-DETR). Specifically, we randomly crop patches from the given image and then feed them as queries to the decoder. The model is pre-trained to detect these query patches from the input image. During the pre-training, we address two critical issues: multi-task learning and multi-query localization. (1) To trade off classification and localization preferences in the pretext task, we find that freezing the CNN backbone is the prerequisite for the success of pre-training transformers. (2) To perform multi-query localization, we develop UP-DETR with multi-query patch detection with attention mask. Besides, UP-DETR also provides a unified perspective for fine-tuning object detection and one-shot detection tasks. In our experiments, UP-DETR significantly boosts the performance of DETR with faster convergence and higher average precision on object detection, one-shot detection and panoptic segmentation. Code and pre-training models: https://github.com/dddzg/up-detr.
3D object detection and pose estimation has been studied extensively in recent decades for its potential applications in robotics. However, there still remains challenges when we aim at detecting multiple objects while retaining low false positive rate in cluttered environments. This paper proposes a robust 3D object detection and pose estimation pipeline based on RGB-D images, which can detect multiple objects simultaneously while reducing false positives. Detection begins with template matching and yields a set of template matches. A clustering algorithm then groups templates of similar spatial location and produces multiple-object hypotheses. A scoring function evaluates the hypotheses using their associated templates and non-maximum suppression is adopted to remove duplicate results based on the scores. Finally, a combination of point cloud processing algorithms are used to compute objects' 3D poses. Existing object hypotheses are verified by computing the overlap between model and scene points. Experiments demonstrate that our approach provides competitive results comparable to the state-of-the-arts and can be applied to robot random bin-picking.
Verification and regression are two general methodologies for prediction in neural networks. Each has its own strengths: verification can be easier to infer accurately, and regression is more efficient and applicable to continuous target variables. Hence, it is often beneficial to carefully combine them to take advantage of their benefits. In this paper, we take this philosophy to improve state-of-the-art object detection, specifically by RepPoints. Though RepPoints provides high performance, we find that its heavy reliance on regression for object localization leaves room for improvement. We introduce verification tasks into the localization prediction of RepPoints, producing RepPoints v2, which provides consistent improvements of about 2.0 mAP over the original RepPoints on the COCO object detection benchmark using different backbones and training methods. RepPoints v2 also achieves 52.1 mAP on COCO \texttt{test-dev} by a single model. Moreover, we show that the proposed approach can more generally elevate other object detection frameworks as well as applications such as instance segmentation. The code is available at https://github.com/Scalsol/RepPointsV2.
In this work, we compare the detection accuracy and speed of several state-of-the-art models for the task of detecting oil and gas fracking wells and small cars in commercial electro-optical satellite imagery. Several models are studied from the single-stage, two-stage, and multi-stage object detection families of techniques. For the detection of fracking well pads (50m - 250m), we find single-stage detectors provide superior prediction speed while also matching detection performance of their two and multi-stage counterparts. However, for detecting small cars, two-stage and multi-stage models provide substantially higher accuracies at the cost of some speed. We also measure timing results of the sliding window object detection algorithm to provide a baseline for comparison. Some of these models have been incorporated into the Lockheed Martin Globally-Scalable Automated Target Recognition (GATR) framework.
Object detection is one of the most important and fundamental aspects of computer vision tasks, which has been broadly utilized in pose estimation, object tracking and instance segmentation models. To obtain training data for object detection model efficiently, many datasets opt to obtain their unannotated data in video format and the annotator needs to draw a bounding box around each object in the images. Annotating every frame from a video is costly and inefficient since many frames contain very similar information for the model to learn from. How to select the most informative frames from a video to annotate has become a highly practical task to solve but attracted little attention in research. In this paper, we proposed a novel active learning algorithm for object detection models to tackle this problem. In the proposed active learning algorithm, both classification and localization informativeness of unlabelled data are measured and aggregated. Utilizing the temporal information from video frames, two novel localization informativeness measurements are proposed. Furthermore, a weight curve is proposed to avoid querying adjacent frames. Proposed active learning algorithm with multiple configurations was evaluated on the MuPoTS dataset and FootballPD dataset.