We introduce point affiliation into feature upsampling, a notion that describes the affiliation of each upsampled point to a semantic cluster formed by local decoder feature points with semantic similarity. By rethinking point affiliation, we present a generic formulation for generating upsampling kernels. The kernels encourage not only semantic smoothness but also boundary sharpness in the upsampled feature maps. Such properties are particularly useful for some dense prediction tasks such as semantic segmentation. The key idea of our formulation is to generate similarity-aware kernels by comparing the similarity between each encoder feature point and the spatially associated local region of decoder features. In this way, the encoder feature point can function as a cue to inform the semantic cluster of upsampled feature points. To embody the formulation, we further instantiate a lightweight upsampling operator, termed Similarity-Aware Point Affiliation (SAPA), and investigate its variants. SAPA invites consistent performance improvements on a number of dense prediction tasks, including semantic segmentation, object detection, depth estimation, and image matting. Code is available at: https://github.com/poppinace/sapa
Multi-agent collaborative perception could significantly upgrade the perception performance by enabling agents to share complementary information with each other through communication. It inevitably results in a fundamental trade-off between perception performance and communication bandwidth. To tackle this bottleneck issue, we propose a spatial confidence map, which reflects the spatial heterogeneity of perceptual information. It empowers agents to only share spatially sparse, yet perceptually critical information, contributing to where to communicate. Based on this novel spatial confidence map, we propose Where2comm, a communication-efficient collaborative perception framework. Where2comm has two distinct advantages: i) it considers pragmatic compression and uses less communication to achieve higher perception performance by focusing on perceptually critical areas; and ii) it can handle varying communication bandwidth by dynamically adjusting spatial areas involved in communication. To evaluate Where2comm, we consider 3D object detection in both real-world and simulation scenarios with two modalities (camera/LiDAR) and two agent types (cars/drones) on four datasets: OPV2V, V2X-Sim, DAIR-V2X, and our original CoPerception-UAVs. Where2comm consistently outperforms previous methods; for example, it achieves more than $100,000 \times$ lower communication volume and still outperforms DiscoNet and V2X-ViT on OPV2V. Our code is available at https://github.com/MediaBrain-SJTU/where2comm.
Can we see it all? Do we know it All? These are questions thrown to human beings in our contemporary society to evaluate our tendency to solve problems. Recent studies have explored several models in object detection; however, most have failed to meet the demand for objectiveness and predictive accuracy, especially in developing and under-developed countries. Consequently, several global security threats have necessitated the development of efficient approaches to tackle these issues. This paper proposes an object detection model for cyber-physical systems known as Smart Surveillance Systems (3s). This research proposes a 2-phase approach, highlighting the advantages of YOLO v3 deep learning architecture in real-time and visual object detection. A transfer learning approach was implemented for this research to reduce training time and computing resources. The dataset utilized for training the model is the MS COCO dataset which contains 328,000 annotated image instances. Deep learning techniques such as Pre-processing, Data pipelining, and detection was implemented to improve efficiency. Compared to other novel research models, the proposed model's results performed exceedingly well in detecting WILD objects in surveillance footages. An accuracy of 99.71% was recorded, with an improved mAP of 61.5.
Smart monitoring using three-dimensional (3D) image sensors has been attracting attention in the context of smart cities. In smart monitoring, object detection from point cloud data acquired by 3D image sensors is implemented for detecting moving objects such as vehicles and pedestrians to ensure safety on the road. However, the features of point cloud data are diversified due to the characteristics of light detection and ranging (LIDAR) units used as 3D image sensors or the install position of the 3D image sensors. Although a variety of deep learning (DL) models for object detection from point cloud data have been studied to date, no research has considered how to use multiple DL models in accordance with the features of the point cloud data. In this work, we propose a feature-based model selection framework that creates various DL models by using multiple DL methods and by utilizing training data with pseudo incompleteness generated by two artificial techniques: sampling and noise adding. It selects the most suitable DL model for the object detection task in accordance with the features of the point cloud data acquired in the real environment. To demonstrate the effectiveness of the proposed framework, we compare the performance of multiple DL models using benchmark datasets created from the KITTI dataset and present example results of object detection obtained through a real outdoor experiment. Depending on the situation, the detection accuracy varies up to 32% between DL models, which confirms the importance of selecting an appropriate DL model according to the situation.
Automatic traffic accidents detection has appealed to the machine vision community due to its implications on the development of autonomous intelligent transportation systems (ITS) and importance to traffic safety. Most previous studies on efficient analysis and prediction of traffic accidents, however, have used small-scale datasets with limited coverage, which limits their effect and applicability. Existing datasets in traffic accidents are either small-scale, not from surveillance cameras, not open-sourced, or not built for freeway scenes. Since accidents happened in freeways tend to cause serious damage and are too fast to catch the spot. An open-sourced datasets targeting on freeway traffic accidents collected from surveillance cameras is in great need and of practical importance. In order to help the vision community address these shortcomings, we endeavor to collect video data of real traffic accidents that covered abundant scenes. After integration and annotation by various dimensions, a large-scale traffic accidents dataset named TAD is proposed in this work. Various experiments on image classification, object detection, and video classification tasks, using public mainstream vision algorithms or frameworks are conducted in this work to demonstrate performance of different methods. The proposed dataset together with the experimental results are presented as a new benchmark to improve computer vision research, especially in ITS.
Leveraging multi-modal fusion, especially between camera and LiDAR, has become essential for building accurate and robust 3D object detection systems for autonomous vehicles. Until recently, point decorating approaches, in which point clouds are augmented with camera features, have been the dominant approach in the field. However, these approaches fail to utilize the higher resolution images from cameras. Recent works projecting camera features to the bird's-eye-view (BEV) space for fusion have also been proposed, however they require projecting millions of pixels, most of which only contain background information. In this work, we propose a novel approach Center Feature Fusion (CFF), in which we leverage center-based detection networks in both the camera and LiDAR streams to identify relevant object locations. We then use the center-based detection to identify the locations of pixel features relevant to object locations, a small fraction of the total number in the image. These are then projected and fused in the BEV frame. On the nuScenes dataset, we outperform the LiDAR-only baseline by 4.9% mAP while fusing up to 100x fewer features than other fusion methods.
We propose DeepFusion, a modular multi-modal architecture to fuse lidars, cameras and radars in different combinations for 3D object detection. Specialized feature extractors take advantage of each modality and can be exchanged easily, making the approach simple and flexible. Extracted features are transformed into bird's-eye-view as a common representation for fusion. Spatial and semantic alignment is performed prior to fusing modalities in the feature space. Finally, a detection head exploits rich multi-modal features for improved 3D detection performance. Experimental results for lidar-camera, lidar-camera-radar and camera-radar fusion show the flexibility and effectiveness of our fusion approach. In the process, we study the largely unexplored task of faraway car detection up to 225 meters, showing the benefits of our lidar-camera fusion. Furthermore, we investigate the required density of lidar points for 3D object detection and illustrate implications at the example of robustness against adverse weather conditions. Moreover, ablation studies on our camera-radar fusion highlight the importance of accurate depth estimation.
There is a longstanding interest in capturing the error behaviour of object detectors by finding images where their performance is likely to be unsatisfactory. In real-world applications such as autonomous driving, it is also crucial to characterise potential failures beyond simple requirements of detection performance. For example, a missed detection of a pedestrian close to an ego vehicle will generally require closer inspection than a missed detection of a car in the distance. The problem of predicting such potential failures at test time has largely been overlooked in the literature and conventional approaches based on detection uncertainty fall short in that they are agnostic to such fine-grained characterisation of errors. In this work, we propose to reformulate the problem of finding "hard" images as a query-based hard image retrieval task, where queries are specific definitions of "hardness", and offer a simple and intuitive method that can solve this task for a large family of queries. Our method is entirely post-hoc, does not require ground-truth annotations, is independent of the choice of a detector, and relies on an efficient Monte Carlo estimation that uses a simple stochastic model in place of the ground-truth. We show experimentally that it can be applied successfully to a wide variety of queries for which it can reliably identify hard images for a given detector without any labelled data. We provide results on ranking and classification tasks using the widely used RetinaNet, Faster-RCNN, Mask-RCNN, and Cascade Mask-RCNN object detectors. The code for this project is available at https://github.com/fiveai/hardest.
Despite their recent success, deep neural networks continue to perform poorly when they encounter distribution shifts at test time. Many recently proposed approaches try to counter this by aligning the model to the new distribution prior to inference. With no labels available this requires unsupervised objectives to adapt the model on the observed test data. In this paper, we propose Test-Time Self-Training (TeST): a technique that takes as input a model trained on some source data and a novel data distribution at test time, and learns invariant and robust representations using a student-teacher framework. We find that models adapted using TeST significantly improve over baseline test-time adaptation algorithms. TeST achieves competitive performance to modern domain adaptation algorithms, while having access to 5-10x less data at time of adaption. We thoroughly evaluate a variety of baselines on two tasks: object detection and image segmentation and find that models adapted with TeST. We find that TeST sets the new state-of-the art for test-time domain adaptation algorithms.
3D object detection with multi-sensors is essential for an accurate and reliable perception system of autonomous driving and robotics. Existing 3D detectors significantly improve the accuracy by adopting a two-stage paradigm which merely relies on LiDAR point clouds for 3D proposal refinement. Though impressive, the sparsity of point clouds, especially for the points far away, making it difficult for the LiDAR-only refinement module to accurately recognize and locate objects.To address this problem, we propose a novel multi-modality two-stage approach named FusionRCNN, which effectively and efficiently fuses point clouds and camera images in the Regions of Interest(RoI). FusionRCNN adaptively integrates both sparse geometry information from LiDAR and dense texture information from camera in a unified attention mechanism. Specifically, it first utilizes RoIPooling to obtain an image set with a unified size and gets the point set by sampling raw points within proposals in the RoI extraction step; then leverages an intra-modality self-attention to enhance the domain-specific features, following by a well-designed cross-attention to fuse the information from two modalities.FusionRCNN is fundamentally plug-and-play and supports different one-stage methods with almost no architectural changes. Extensive experiments on KITTI and Waymo benchmarks demonstrate that our method significantly boosts the performances of popular detectors.Remarkably, FusionRCNN significantly improves the strong SECOND baseline by 6.14% mAP on Waymo, and outperforms competing two-stage approaches. Code will be released soon at https://github.com/xxlbigbrother/Fusion-RCNN.
Under the domain shift, cross-domain few-shot object detection aims to adapt object detectors in the target domain with a few annotated target data. There exists two significant challenges: (1) Highly insufficient target domain data; (2) Potential over-adaptation and misleading caused by inappropriately amplified target samples without any restriction. To address these challenges, we propose an adaptive method consisting of two parts. First, we propose an adaptive optimization strategy to select augmented data similar to target samples rather than blindly increasing the amount. Specifically, we filter the augmented candidates which significantly deviate from the target feature distribution in the very beginning. Second, to further relieve the data limitation, we propose the multi-level domain-aware data augmentation to increase the diversity and rationality of augmented data, which exploits the cross-image foreground-background mixture. Experiments show that the proposed method achieves state-of-the-art performance on multiple benchmarks.
Repair and maintenance of underwater structures as well as marine science rely heavily on the results of underwater object detection, which is a crucial part of the image processing workflow. Although many computer vision-based approaches have been presented, no one has yet developed a system that reliably and accurately detects and categorizes objects and animals found in the deep sea. This is largely due to obstacles that scatter and absorb light in an underwater setting. With the introduction of deep learning, scientists have been able to address a wide range of issues, including safeguarding the marine ecosystem, saving lives in an emergency, preventing underwater disasters, and detecting, spooring, and identifying underwater targets. However, the benefits and drawbacks of these deep learning systems remain unknown. Therefore, the purpose of this article is to provide an overview of the dataset that has been utilized in underwater object detection and to present a discussion of the advantages and disadvantages of the algorithms employed for this purpose.
Deep learning has led to great progress in the detection of mobile (i.e. movement-capable) objects in urban driving scenes in recent years. Supervised approaches typically require the annotation of large training sets; there has thus been great interest in leveraging weakly, semi- or self-supervised methods to avoid this, with much success. Whilst weakly and semi-supervised methods require some annotation, self-supervised methods have used cues such as motion to relieve the need for annotation altogether. However, a complete absence of annotation typically degrades their performance, and ambiguities that arise during motion grouping can inhibit their ability to find accurate object boundaries. In this paper, we propose a new self-supervised mobile object detection approach called SCT. This uses both motion cues and expected object sizes to improve detection performance, and predicts a dense grid of 3D oriented bounding boxes to improve object discovery. We significantly outperform the state-of-the-art self-supervised mobile object detection method TCR on the KITTI tracking benchmark, and achieve performance that is within 30% of the fully supervised PV-RCNN++ method for IoUs <= 0.5.
Without densely tiled anchor boxes or grid points in the image, sparse R-CNN achieves promising results through a set of object queries and proposal boxes updated in the cascaded training manner. However, due to the sparse nature and the one-to-one relation between the query and its attending region, it heavily depends on the self attention, which is usually inaccurate in the early training stage. Moreover, in a scene of dense objects, the object query interacts with many irrelevant ones, reducing its uniqueness and harming the performance. This paper proposes to use IoU between different boxes as a prior for the value routing in self attention. The original attention matrix multiplies the same size matrix computed from the IoU of proposal boxes, and they determine the routing scheme so that the irrelevant features can be suppressed. Furthermore, to accurately extract features for both classification and regression, we add two lightweight projection heads to provide the dynamic channel masks based on object query, and they multiply with the output from dynamic convs, making the results suitable for the two different tasks. We validate the proposed scheme on different datasets, including MS-COCO and CrowdHuman, showing that it significantly improves the performance and increases the model convergence speed.
Bounded by the inherent ambiguity of depth perception, contemporary camera-based 3D object detection methods fall into the performance bottleneck. Intuitively, leveraging temporal multi-view stereo (MVS) technology is the natural knowledge for tackling this ambiguity. However, traditional attempts of MVS are flawed in two aspects when applying to 3D object detection scenes: 1) The affinity measurement among all views suffers expensive computation cost; 2) It is difficult to deal with outdoor scenarios where objects are often mobile. To this end, we introduce an effective temporal stereo method to dynamically select the scale of matching candidates, enable to significantly reduce computation overhead. Going one step further, we design an iterative algorithm to update more valuable candidates, making it adaptive to moving candidates. We instantiate our proposed method to multi-view 3D detector, namely BEVStereo. BEVStereo achieves the new state-of-the-art performance (i.e., 52.5% mAP and 61.0% NDS) on the camera-only track of nuScenes dataset. Meanwhile, extensive experiments reflect our method can deal with complex outdoor scenarios better than contemporary MVS approaches. Codes have been released at https://github.com/Megvii-BaseDetection/BEVStereo.
RGB-Thermal salient object detection (SOD) combines two spectra to segment visually conspicuous regions in images. Most existing methods use boundary maps to learn the sharp boundary. These methods ignore the interactions between isolated boundary pixels and other confident pixels, leading to sub-optimal performance. To address this problem,we propose a position-aware relation learning network (PRLNet) for RGB-T SOD based on swin transformer. PRLNet explores the distance and direction relationships between pixels to strengthen intra-class compactness and inter-class separation, generating salient object masks with clear boundaries and homogeneous regions. Specifically, we develop a novel signed distance map auxiliary module (SDMAM) to improve encoder feature representation, which takes into account the distance relation of different pixels in boundary neighborhoods. Then, we design a feature refinement approach with directional field (FRDF), which rectifies features of boundary neighborhood by exploiting the features inside salient objects. FRDF utilizes the directional information between object pixels to effectively enhance the intra-class compactness of salient regions. In addition, we constitute a pure transformer encoder-decoder network to enhance multispectral feature representation for RGB-T SOD. Finally, we conduct quantitative and qualitative experiments on three public benchmark datasets.The results demonstrate that our proposed method outperforms the state-of-the-art methods.
In this work, we consider the safety-oriented performance of 3D object detectors in autonomous driving contexts. Specifically, despite impressive results shown by the mass literature, developers often find it hard to ensure the safe deployment of these learning-based perception models. Attributing the challenge to the lack of safety-oriented metrics, we hereby present uncompromising spatial constraints (USC), which characterize a simple yet important localization requirement demanding the predictions to fully cover the objects when seen from the autonomous vehicle. The constraints, as we formulate using the perspective and bird's-eye views, can be naturally reflected by quantitative measures, such that having an object detector with a higher score implies a lower risk of collision. Finally, beyond model evaluation, we incorporate the quantitative measures into common loss functions to enable safety-oriented fine-tuning for existing models. With experiments using the nuScenes dataset and a closed-loop simulation, our work demonstrates such considerations of safety notions at the perception level not only improve model performances beyond accuracy but also allow for a more direct linkage to actual system safety.
Open-world object detection, as a more general and challenging goal, aims to recognize and localize objects described by arbitrary category names. The recent work GLIP formulates this problem as a grounding problem by concatenating all category names of detection datasets into sentences, which leads to inefficient interaction between category names. This paper presents DetCLIP, a paralleled visual-concept pre-training method for open-world detection by resorting to knowledge enrichment from a designed concept dictionary. To achieve better learning efficiency, we propose a novel paralleled concept formulation that extracts concepts separately to better utilize heterogeneous datasets (i.e., detection, grounding, and image-text pairs) for training. We further design a concept dictionary~(with descriptions) from various online sources and detection datasets to provide prior knowledge for each concept. By enriching the concepts with their descriptions, we explicitly build the relationships among various concepts to facilitate the open-domain learning. The proposed concept dictionary is further used to provide sufficient negative concepts for the construction of the word-region alignment loss\, and to complete labels for objects with missing descriptions in captions of image-text pair data. The proposed framework demonstrates strong zero-shot detection performances, e.g., on the LVIS dataset, our DetCLIP-T outperforms GLIP-T by 9.9% mAP and obtains a 13.5% improvement on rare categories compared to the fully-supervised model with the same backbone as ours.
LiDAR-based 3D object detection, semantic segmentation, and panoptic segmentation are usually implemented in specialized networks with distinctive architectures that are difficult to adapt to each other. This paper presents LidarMultiNet, a LiDAR-based multi-task network that unifies these three major LiDAR perception tasks. Among its many benefits, a multi-task network can reduce the overall cost by sharing weights and computation among multiple tasks. However, it typically underperforms compared to independently combined single-task models. The proposed LidarMultiNet aims to bridge the performance gap between the multi-task network and multiple single-task networks. At the core of LidarMultiNet is a strong 3D voxel-based encoder-decoder architecture with a Global Context Pooling (GCP) module extracting global contextual features from a LiDAR frame. Task-specific heads are added on top of the network to perform the three LiDAR perception tasks. More tasks can be implemented simply by adding new task-specific heads while introducing little additional cost. A second stage is also proposed to refine the first-stage segmentation and generate accurate panoptic segmentation results. LidarMultiNet is extensively tested on both Waymo Open Dataset and nuScenes dataset, demonstrating for the first time that major LiDAR perception tasks can be unified in a single strong network that is trained end-to-end and achieves state-of-the-art performance. Notably, LidarMultiNet reaches the official 1st place in the Waymo Open Dataset 3D semantic segmentation challenge 2022 with the highest mIoU and the best accuracy for most of the 22 classes on the test set, using only LiDAR points as input. It also sets the new state-of-the-art for a single model on the Waymo 3D object detection benchmark and three nuScenes benchmarks.
There have been attempts to detect 3D objects by fusion of stereo camera images and LiDAR sensor data or using LiDAR for pre-training and only monocular images for testing, but there have been less attempts to use only monocular image sequences due to low accuracy. In addition, when depth prediction using only monocular images, only scale-inconsistent depth can be predicted, which is the reason why researchers are reluctant to use monocular images alone. Therefore, we propose a method for predicting absolute depth and detecting 3D objects using only monocular image sequences by enabling end-to-end learning of detection networks and depth prediction networks. As a result, the proposed method surpasses other existing methods in performance on the KITTI 3D dataset. Even when monocular image and 3D LiDAR are used together during training in an attempt to improve performance, ours exhibit is the best performance compared to other methods using the same input. In addition, end-to-end learning not only improves depth prediction performance, but also enables absolute depth prediction, because our network utilizes the fact that the size of a 3D object such as a car is determined by the approximate size.