With the end goal of selecting and using diver detection models to support human-robot collaboration capabilities such as diver following, we thoroughly analyze a large set of deep neural networks for diver detection. We begin by producing a dataset of approximately 105,000 annotated images of divers sourced from videos -- one of the largest and most varied diver detection datasets ever created. Using this dataset, we train a variety of state-of-the-art deep neural networks for object detection, including SSD with Mobilenet, Faster R-CNN, and YOLO. Along with these single-frame detectors, we also train networks designed for detection of objects in a video stream, using temporal information as well as single-frame image information. We evaluate these networks on typical accuracy and efficiency metrics, as well as on the temporal stability of their detections. Finally, we analyze the failures of these detectors, pointing out the most common scenarios of failure. Based on our results, we recommend SSDs or Tiny-YOLOv4 for real-time applications on robots and recommend further investigation of video object detection methods.
The strong demand of autonomous driving in the industry has lead to strong interest in 3D object detection and resulted in many excellent 3D object detection algorithms. However, the vast majority of algorithms only model single-frame data, ignoring the temporal information of the sequence of data. In this work, we propose a new transformer, called Temporal-Channel Transformer, to model the spatial-temporal domain and channel domain relationships for video object detecting from Lidar data. As a special design of this transformer, the information encoded in the encoder is different from that in the decoder, i.e. the encoder encodes temporal-channel information of multiple frames while the decoder decodes the spatial-channel information for the current frame in a voxel-wise manner. Specifically, the temporal-channel encoder of the transformer is designed to encode the information of different channels and frames by utilizing the correlation among features from different channels and frames. On the other hand, the spatial decoder of the transformer will decode the information for each location of the current frame. Before conducting the object detection with detection head, the gate mechanism is deployed for re-calibrating the features of current frame, which filters out the object irrelevant information by repetitively refine the representation of target frame along with the up-sampling process. Experimental results show that we achieve the state-of-the-art performance in grid voxel-based 3D object detection on the nuScenes benchmark.
In this paper, we propose a new video object detector (VoD) method referred to as temporal feature aggregation and motion-aware VoD (TM-VoD), which produces a joint representation of temporal image sequences and object motion. The proposed TM-VoD aggregates visual feature maps extracted by convolutional neural networks applying the temporal attention gating and spatial feature alignment. This temporal feature aggregation is performed in two stages in a hierarchical fashion. In the first stage, the visual feature maps are fused at a pixel level via gated attention model. In the second stage, the proposed method aggregates the features after aligning the object features using temporal box offset calibration and weights them according to the cosine similarity measure. The proposed TM-VoD also finds the representation of the motion of objects in two successive steps. The pixel-level motion features are first computed based on the incremental changes between the adjacent visual feature maps. Then, box-level motion features are obtained from both the region of interest (RoI)-aligned pixel-level motion features and the sequential changes of the box coordinates. Finally, all these features are concatenated to produce a joint representation of the objects for VoD. The experiments conducted on the ImageNet VID dataset demonstrate that the proposed method outperforms existing VoD methods and achieves a performance comparable to that of state-of-the-art VoDs.
There is lots of scientific work about object detection in images. For many applications like for example autonomous driving the actual data on which classification has to be done are videos. This work compares different methods, especially those which use Recurrent Neural Networks to detect objects in videos. We differ between feature-based methods, which feed feature maps of different frames into the recurrent units, box-level methods, which feed bounding boxes with class probabilities into the recurrent units and methods which use flow networks. This study indicates common outcomes of the compared methods like the benefit of including the temporal context into object detection and states conclusions and guidelines for video object detection networks.
We present an Object-aware Feature Aggregation (OFA) module for video object detection (VID). Our approach is motivated by the intriguing property that video-level object-aware knowledge can be employed as a powerful semantic prior to help object recognition. As a consequence, augmenting features with such prior knowledge can effectively improve the classification and localization performance. To make features get access to more content about the whole video, we first capture the object-aware knowledge of proposals and incorporate such knowledge with the well-established pair-wise contexts. With extensive experimental results on the ImageNet VID dataset, our approach demonstrates the effectiveness of object-aware knowledge with the superior performance of 83.93% and 86.09% mAP with ResNet-101 and ResNeXt-101, respectively. When further equipped with Sequence DIoU NMS, we obtain the best-reported mAP of 85.07% and 86.88% upon the paper submitted. The code to reproduce our results will be released after acceptance.
Advanced video analytic systems, including scene classification and object detection, have seen widespread success in various domains such as smart cities and autonomous transportation. With an ever-growing number of powerful client devices, there is incentive to move these heavy video analytics workloads from the cloud to mobile devices to achieve low latency and real-time processing and to preserve user privacy. However, most video analytic systems are heavyweight and are trained offline with some pre-defined latency or accuracy requirements. This makes them unable to adapt at runtime in the face of three types of dynamism -- the input video characteristics change, the amount of compute resources available on the node changes due to co-located applications, and the user's latency-accuracy requirements change. In this paper we introduce ApproxDet, an adaptive video object detection framework for mobile devices to meet accuracy-latency requirements in the face of changing content and resource contention scenarios. To achieve this, we introduce a multi-branch object detection kernel (layered on Faster R-CNN), which incorporates a data-driven modeling approach on the performance metrics, and a latency SLA-driven scheduler to pick the best execution branch at runtime. We couple this kernel with approximable video object tracking algorithms to create an end-to-end video object detection system. We evaluate ApproxDet on a large benchmark video dataset and compare quantitatively to AdaScale and YOLOv3. We find that ApproxDet is able to adapt to a wide variety of contention and content characteristics and outshines all baselines, e.g., it achieves 52% lower latency and 11.1% higher accuracy over YOLOv3.
Object recognition in video is an important task for plenty of applications, including autonomous driving perception, surveillance tasks, wearable devices or IoT networks. Object recognition using video data is more challenging than using still images due to blur, occlusions or rare object poses. Specific video detectors with high computational cost or standard image detectors together with a fast post-processing algorithm achieve the current state-of-the-art. This work introduces a novel post-processing pipeline that overcomes some of the limitations of previous post-processing methods by introducing a learning-based similarity evaluation between detections across frames. Our method improves the results of state-of-the-art specific video detectors, specially regarding fast moving objects, and presents low resource requirements. And applied to efficient still image detectors, such as YOLO, provides comparable results to much more computationally intensive detectors.
Optical flow, which expresses pixel displacement, is widely used in many computer vision tasks to provide pixel-level motion information. However, with the remarkable progress of the convolutional neural network, recent state-of-the-art approaches are proposed to solve problems directly on feature-level. Since the displacement of feature vector is not consistent to the pixel displacement, a common approach is to:forward optical flow to a neural network and fine-tune this network on the task dataset. With this method,they expect the fine-tuned network to produce tensors encoding feature-level motion information. In this paper, we rethink this de facto paradigm and analyze its drawbacks in the video object detection task. To mitigate these issues, we propose a novel network (IFF-Net) with an \textbf{I}n-network \textbf{F}eature \textbf{F}low estimation module (IFF module) for video object detection. Without resorting pre-training on any additional dataset, our IFF module is able to directly produce \textbf{feature flow} which indicates the feature displacement. Our IFF module consists of a shallow module, which shares the features with the detection branches. This compact design enables our IFF-Net to accurately detect objects, while maintaining a fast inference speed. Furthermore, we propose a transformation residual loss (TRL) based on \textit{self-supervision}, which further improves the performance of our IFF-Net. Our IFF-Net outperforms existing methods and sets a state-of-the-art performance on ImageNet VID.
Video object detection is a tough task due to the deteriorated quality of video sequences captured under complex environments. Currently, this area is dominated by a series of feature enhancement based methods, which distill beneficial semantic information from multiple frames and generate enhanced features through fusing the distilled information. However, the distillation and fusion operations are usually performed at either frame level or instance level with external guidance using additional information, such as optical flow and feature memory. In this work, we propose a dual semantic fusion network (abbreviated as DSFNet) to fully exploit both frame-level and instance-level semantics in a unified fusion framework without external guidance. Moreover, we introduce a geometric similarity measure into the fusion process to alleviate the influence of information distortion caused by noise. As a result, the proposed DSFNet can generate more robust features through the multi-granularity fusion and avoid being affected by the instability of external guidance. To evaluate the proposed DSFNet, we conduct extensive experiments on the ImageNet VID dataset. Notably, the proposed dual semantic fusion network achieves, to the best of our knowledge, the best performance of 84.1\% mAP among the current state-of-the-art video object detectors with ResNet-101 and 85.4\% mAP with ResNeXt-101 without using any post-processing steps.
New machine learning accelerators are being announced and released each month for a variety of applications from speech recognition, video object detection, assisted driving, and many data center applications. This paper updates the survey of of AI accelerators and processors from last year's IEEE-HPEC paper. This paper collects and summarizes the current accelerators that have been publicly announced with performance and power consumption numbers. The performance and power values are plotted on a scatter graph and a number of dimensions and observations from the trends on this plot are discussed and analyzed. For instance, there are interesting trends in the plot regarding power consumption, numerical precision, and inference versus training. This year, there are many more announced accelerators that are implemented with many more architectures and technologies from vector engines, dataflow engines, neuromorphic designs, flash-based analog memory processing, and photonic-based processing.
Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training. However, major challenges remain: (1) differentiation of object instances can be ambiguous; (2) detectors tend to focus on discriminative parts rather than entire objects; (3) without ground truth, object proposals have to be redundant for high recalls, causing significant memory consumption. Addressing these challenges is difficult, as it often requires to eliminate uncertainties and trivial solutions. To target these issues we develop an instance-aware and context-focused unified framework. It employs an instance-aware self-training algorithm and a learnable Concrete DropBlock while devising a memory-efficient sequential batch back-propagation. Our proposed method achieves state-of-the-art results on COCO ($12.1\% ~AP$, $24.8\% ~AP_{50}$), VOC 2007 ($54.9\% ~AP$), and VOC 2012 ($52.1\% ~AP$), improving baselines by great margins. In addition, the proposed method is the first to benchmark ResNet based models and weakly supervised video object detection. Code, models, and more details will be made available at: https://github.com/NVlabs/wetectron.
Existing LiDAR-based 3D object detectors usually focus on the single-frame detection, while ignoring the spatiotemporal information in consecutive point cloud frames. In this paper, we propose an end-to-end online 3D video object detector that operates on point cloud sequences. The proposed model comprises a spatial feature encoding component and a spatiotemporal feature aggregation component. In the former component, a novel Pillar Message Passing Network (PMPNet) is proposed to encode each discrete point cloud frame. It adaptively collects information for a pillar node from its neighbors by iterative message passing, which effectively enlarges the receptive field of the pillar feature. In the latter component, we propose an Attentive Spatiotemporal Transformer GRU (AST-GRU) to aggregate the spatiotemporal information, which enhances the conventional ConvGRU with an attentive memory gating mechanism. AST-GRU contains a Spatial Transformer Attention (STA) module and a Temporal Transformer Attention (TTA) module, which can emphasize the foreground objects and align the dynamic objects, respectively. Experimental results demonstrate that the proposed 3D video object detector achieves state-of-the-art performance on the large-scale nuScenes benchmark.
How do humans recognize an object in a piece of video? Due to the deteriorated quality of single frame, it may be hard for people to identify an occluded object in this frame by just utilizing information within one image. We argue that there are two important cues for humans to recognize objects in videos: the global semantic information and the local localization information. Recently, plenty of methods adopt the self-attention mechanisms to enhance the features in key frame with either global semantic information or local localization information. In this paper we introduce memory enhanced global-local aggregation (MEGA) network, which is among the first trials that takes full consideration of both global and local information. Furthermore, empowered by a novel and carefully-designed Long Range Memory (LRM) module, our proposed MEGA could enable the key frame to get access to much more content than any previous methods. Enhanced by these two sources of information, our method achieves state-of-the-art performance on ImageNet VID dataset. Code is available at \url{https://github.com/Scalsol/mega.pytorch}.
Consecutive frames in a video are highly redundant. Therefore, to perform the task of video object detection, executing single frame detectors on every frame without reusing any information is quite wasteful. It is with this idea in mind that we propose RN-VID (standing for RetinaNet-VIDeo), a novel approach to video object detection. Our contributions are twofold. First, we propose a new architecture that allows the usage of information from nearby frames to enhance feature maps. Second, we propose a novel module to merge feature maps of same dimensions using re-ordering of channels and 1 x 1 convolutions. We then demonstrate that RN-VID achieves better mean average precision (mAP) than corresponding single frame detectors with little additional cost during inference.
Video object detection targets to simultaneously localize the bounding boxes of the objects and identify their classes in a given video. One challenge for video object detection is to consistently detect all objects across the whole video. As the appearance of objects may deteriorate in some frames, features or detections from the other frames are commonly used to enhance the prediction. In this paper, we propose a Plug & Play scale-adaptive convolutional regression tracker for the video object detection task, which could be easily and compatibly implanted into the current state-of-the-art detection networks. As the tracker reuses the features from the detector, it is a very light-weighted increment to the detection network. The whole network performs at the speed close to a standard object detector. With our new video object detection pipeline design, image object detectors can be easily turned into efficient video object detectors without modifying any parameters. The performance is evaluated on the large-scale ImageNet VID dataset. Our Plug & Play design improves mAP score for the image detector by around 5% with only little speed drop.
Drones, or general UAVs, equipped with cameras have been fast deployed with a wide range of applications, including agriculture, aerial photography, and surveillance. Consequently, automatic understanding of visual data collected from drones becomes highly demanding, bringing computer vision and drones more and more closely. To promote and track the developments of object detection and tracking algorithms, we have organized three challenge workshops in conjunction with ECCV 2018, ICCV 2019 and ECCV 2020, attracting more than 100 teams around the world. We provide a large-scale drone captured dataset, VisDrone, which includes four tracks, i.e., (1) image object detection, (2) video object detection, (3) single object tracking, and (4) multi-object tracking. In this paper, we first present a thorough review of object detection and tracking datasets and benchmarks, and discuss the challenges of collecting large-scale drone-based object detection and tracking datasets with fully manual annotations. After that, we describe our VisDrone dataset, which is captured over various urban/suburban areas of 14 different cities across China from North to South. Being the largest such dataset ever published, VisDrone enables extensive evaluation and investigation of visual analysis algorithms for the drone platform. We provide a detailed analysis of the current state of the field of large-scale object detection and tracking on drones, and conclude the challenge as well as propose future directions. We expect the benchmark largely boost the research and development in video analysis on drone platforms. All the datasets and experimental results can be downloaded from https://github.com/VisDrone/VisDrone-Dataset.
Video object detection (VID) has been vigorously studied for years but almost all literature adopts a static accuracy-based evaluation, i.e., average precision (AP). From a robotic perspective, the importance of recall continuity and localization stability is equal to that of accuracy, but the AP is insufficient to reflect detectors' performance across time. In this paper, non-reference assessments are proposed for continuity and stability based on object tracklets. These temporal evaluations can serve as supplements to static AP. Further, we develop an online tracklet refinement for improving detectors' temporal performance through short tracklet suppression, fragment filling, and temporal location fusion. In addition, we propose a small-overlap suppression to extend VID methods to single object tracking (SOT) task so that a flexible SOT-by-detection framework is then formed. Extensive experiments are conducted on ImageNet VID dataset and real-world robotic tasks, where the superiority of our proposed approaches are validated and verified. Codes will be publicly available.
In static monitoring cameras, useful contextual information can stretch far beyond the few seconds typical video understanding models might see: subjects may exhibit similar behavior over multiple days, and background objects remain static. Due to power and storage constraints, sampling frequencies are low, often no faster than one frame per second, and sometimes are irregular due to the use of a motion trigger. In order to perform well in this setting, models must be robust to irregular sampling rates. In this paper we propose a method that leverages temporal context from the unlabeled frames of a novel camera to improve performance at that camera. Specifically, we propose an attention-based approach that allows our model, Context R-CNN, to index into a long term memory bank constructed on a per-camera basis and aggregate contextual features from other frames to boost object detection performance on the current frame. We apply Context R-CNN to two settings: (1) species detection using camera traps, and (2) vehicle detection in traffic cameras, showing in both settings that Context R-CNN leads to performance gains over strong baselines. Moreover, we show that increasing the contextual time horizon leads to improved results. When applied to camera trap data from the Snapshot Serengeti dataset, Context R-CNN with context from up to a month of images outperforms a single-frame baseline by 17.9% mAP, and outperforms S3D (a 3d convolution based baseline) by 11.2% mAP.
Transferring existing image-based detectors to the video is non-trivial since the quality of frames is always deteriorated by part occlusion, rare pose, and motion blur. Previous approaches exploit to propagate and aggregate features across video frames by using optical flow-warping. However, directly applying image-level optical flow onto the high-level features might not establish accurate spatial correspondences. Therefore, a novel module called Learnable Spatio-Temporal Sampling (LSTS) has been proposed to learn semantic-level correspondences among adjacent frame features accurately. The sampled locations are first randomly initialized, then updated iteratively to find better spatial correspondences guided by detection supervision progressively. Besides, Sparsely Recursive Feature Updating (SRFU) module and Dense Feature Aggregation (DFA) module are also introduced to model temporal relations and enhance per-frame features, respectively. Without bells and whistles, the proposed method achieves state-of-the-art performance on the ImageNet VID dataset with less computational complexity and real-time speed. Code will be made available at https://github.com/jiangzhengkai/LSTS.
In this paper we propose a geometry-aware model for video object detection. Specifically, we consider the setting that cameras can be well approximated as static, e.g. in video surveillance scenarios, and scene pseudo depth maps can therefore be inferred easily from the object scale on the image plane. We make the following contributions: First, we extend the recent anchor-free detector (CornerNet [17]) to video object detections. In order to exploit the spatial-temporal information while maintaining high efficiency, the proposed model accepts video clips as input, and only makes predictions for the starting and the ending frames, i.e. heatmaps of object bounding box corners and the corresponding embeddings for grouping. Second, to tackle the challenge from scale variations in object detection, scene geometry information, e.g. derived depth maps, is explicitly incorporated into deep networks for multi-scale feature selection and for the network prediction. Third, we validate the proposed architectures on an autonomous driving dataset generated from the Carla simulator [5], and on a real dataset for human detection (DukeMTMC dataset [28]). When comparing with the existing competitive single-stage or two-stage detectors, the proposed geometry-aware spatio-temporal network achieves significantly better results.