Autonomous driving systems require huge amounts of data to train. Manual annotation of this data is time-consuming and prohibitively expensive since it involves human resources. Therefore, active learning emerged as an alternative to ease this effort and to make data annotation more manageable. In this paper, we introduce a novel active learning approach for object detection in videos by exploiting temporal coherence. Our active learning criterion is based on the estimated number of errors in terms of false positives and false negatives. The detections obtained by the object detector are used to define the nodes of a graph and tracked forward and backward to temporally link the nodes. Minimizing an energy function defined on this graphical model provides estimates of both false positives and false negatives. Additionally, we introduce a synthetic video dataset, called SYNTHIA-AL, specially designed to evaluate active learning for video object detection in road scenes. Finally, we show that our approach outperforms active learning baselines tested on two datasets.
We propose the first multi-frame video object detection framework trained to detect great apes. It is applicable to challenging camera trap footage in complex jungle environments and extends a traditional feature pyramid architecture by adding self-attention driven feature blending in both the spatial as well as the temporal domain. We demonstrate that this extension can detect distinctive species appearance and motion signatures despite significant partial occlusion. We evaluate the framework using 500 camera trap videos of great apes from the Pan African Programme containing 180K frames, which we manually annotated with accurate per-frame animal bounding boxes. These clips contain significant partial occlusions, challenging lighting, dynamic backgrounds, and natural camouflage effects. We show that our approach performs highly robustly and significantly outperforms frame-based detectors. We also perform detailed ablation studies and validation on the full ILSVRC 2015 VID data corpus to demonstrate wider applicability at adequate performance levels. We conclude that the framework is ready to assist human camera trap inspection efforts. We publish code, weights, and ground truth annotations with this paper.
It has been well recognized that modeling object-to-object relations would be helpful for object detection. Nevertheless, the problem is not trivial especially when exploring the interactions between objects to boost video object detectors. The difficulty originates from the aspect that reliable object relations in a video should depend on not only the objects in the present frame but also all the supportive objects extracted over a long range span of the video. In this paper, we introduce a new design to capture the interactions across the objects in spatio-temporal context. Specifically, we present Relation Distillation Networks (RDN) --- a new architecture that novelly aggregates and propagates object relation to augment object features for detection. Technically, object proposals are first generated via Region Proposal Networks (RPN). RDN then, on one hand, models object relation via multi-stage reasoning, and on the other, progressively distills relation through refining supportive object proposals with high objectness scores in a cascaded manner. The learnt relation verifies the efficacy on both improving object detection in each frame and box linking across frames. Extensive experiments are conducted on ImageNet VID dataset, and superior results are reported when comparing to state-of-the-art methods. More remarkably, our RDN achieves 81.8% and 83.2% mAP with ResNet-101 and ResNeXt-101, respectively. When further equipped with linking and rescoring, we obtain to-date the best reported mAP of 83.8% and 84.7%.
Average precision (AP) is a widely used metric to evaluate detection accuracy of image and video object detectors. In this paper, we analyze object detection from videos and point out that AP alone is not sufficient to capture the temporal nature of video object detection. To tackle this problem, we propose a comprehensive metric, average delay (AD), to measure and compare detection delay. To facilitate delay evaluation, we carefully select a subset of ImageNet VID, which we name as ImageNet VIDT with an emphasis on complex trajectories. By extensively evaluating a wide range of detectors on VIDT, we show that most methods drastically increase the detection delay but still preserve AP well. In other words, AP is not sensitive enough to reflect the temporal characteristics of a video object detector. Our results suggest that video object detection methods should be additionally evaluated with a delay metric, particularly for latency-critical applications such as autonomous vehicle perception.
How can we effectively engineer a computer vision system that is able to interpret videos from unconstrained mobility platforms like UAVs? One promising option is to make use of image restoration and enhancement algorithms from the area of computational photography to improve the quality of the underlying frames in a way that also improves automatic visual recognition. Along these lines, exploratory work is needed to find out which image pre-processing algorithms, in combination with the strongest features and supervised machine learning approaches, are good candidates for difficult scenarios like motion blur, weather, and mis-focus -- all common artifacts in UAV acquired images. This paper summarizes the protocols and results of Track 1 of the UG^2+ Challenge held in conjunction with IEEE/CVF CVPR 2019. The challenge looked at two separate problems: (1) object detection improvement in video, and (2) object classification improvement in video. The challenge made use of the UG^2 (UAV, Glider, Ground) dataset, which is an established benchmark for assessing the interplay between image restoration and enhancement and visual recognition. 16 algorithms were submitted by academic and corporate teams, and a detailed analysis of how they performed on each challenge problem is reported here.
Video objection detection (VID) has been a rising research direction in recent years. A central issue of VID is the appearance degradation of video frames caused by fast motion. This problem is essentially ill-posed for a single frame. Therefore, aggregating features from other frames becomes a natural choice. Existing methods rely heavily on optical flow or recurrent neural networks for feature aggregation. However, these methods emphasize more on the temporally nearby frames. In this work, we argue that aggregating features in the full-sequence level will lead to more discriminative and robust features for video object detection. To achieve this goal, we devise a novel Sequence Level Semantics Aggregation (SELSA) module. We further demonstrate the close relationship between the proposed method and the classic spectral clustering method, providing a novel view for understanding the VID problem. We test the proposed method on the ImageNet VID and the EPIC KITCHENS dataset and achieve new state-of-the-art results. Our method does not need complicated postprocessing methods such as Seq-NMS or Tubelet rescoring, which keeps the pipeline simple and clean.
Recent cutting-edge feature aggregation paradigms for video object detection rely on inferring feature correspondence. The feature correspondence estimation problem is fundamentally difficult due to poor image quality, motion blur, etc, and the results of feature correspondence estimation are unstable. To avoid the problem, we propose a simple but effective feature aggregation framework which operates on the object proposal-level. It learns to enhance each proposal's feature via modeling semantic and spatio-temporal relationships among object proposals from both within a frame and across adjacent frames. Experiments are carried out on the ImageNet VID dataset. Without any bells and whistles, our method obtains 80.3\% mAP on the ImageNet VID dataset, which is superior over the previous state-of-the-arts. The proposed feature aggregation mechanism improves the single frame Faster RCNN baseline by 5.8% mAP. Besides, under the setting of no temporal post-processing, our method outperforms the previous state-of-the-art by 1.4% mAP.
In this paper, we address a novel task, namely weakly-supervised spatio-temporally grounding natural sentence in video. Specifically, given a natural sentence and a video, we localize a spatio-temporal tube in the video that semantically corresponds to the given sentence, with no reliance on any spatio-temporal annotations during training. First, a set of spatio-temporal tubes, referred to as instances, are extracted from the video. We then encode these instances and the sentence using our proposed attentive interactor which can exploit their fine-grained relationships to characterize their matching behaviors. Besides a ranking loss, a novel diversity loss is introduced to train the proposed attentive interactor to strengthen the matching behaviors of reliable instance-sentence pairs and penalize the unreliable ones. Moreover, we also contribute a dataset, called VID-sentence, based on the ImageNet video object detection dataset, to serve as a benchmark for our task. Extensive experimental results demonstrate the superiority of our model over the baseline approaches.
We study the robustness of image classifiers to temporal perturbations derived from videos. As part of this study, we construct two datasets, ImageNet-Vid-Robust and YTBB-Robust , containing a total 57,897 images grouped into 3,139 sets of perceptually similar images. Our datasets were derived from ImageNet-Vid and Youtube-BB respectively and thoroughly re-annotated by human experts for image similarity. We evaluate a diverse array of classifiers pre-trained on ImageNet and show a median classification accuracy drop of 16 and 10 on our two datasets. Additionally, we evaluate three detection models and show that natural perturbations induce both classification as well as localization errors, leading to a median drop in detection mAP of 14 points. Our analysis demonstrates that perturbations occurring naturally in videos pose a substantial and realistic challenge to deploying convolutional neural networks in environments that require both reliable and low-latency predictions
Recent advances in single-frame object detection and segmentation techniques have motivated a wide range of works to extend these methods to process video streams. In this paper, we explore the idea of hard attention aimed for latency-sensitive applications. Instead of reasoning about every frame separately, our method selects and only processes a small sub-window of the frame. Our technique then makes predictions for the full frame based on the sub-windows from previous frames and the update from the current sub-window. The latency reduction by this hard attention mechanism comes at the cost of degraded accuracy. We made two contributions to address this. First, we propose a specialized memory cell that recovers lost context when processing sub-windows. Secondly, we adopt a Q-learning-based policy training strategy that enables our approach to intelligently select the sub-windows such that the staleness in the memory hurts the performance the least. Our experiments suggest that our approach reduces the latency by approximately four times without significantly sacrificing the accuracy on the ImageNet VID video object detection dataset and the DAVIS video object segmentation dataset. We further demonstrate that we can reinvest the saved computation into other parts of the network, and thus resulting in an accuracy increase at a comparable computational cost as the original system and beating other recently proposed state-of-the-art methods in the low latency range.
Successive frames of a video are highly redundant, and the most popular object detection methods do not take advantage of this fact. Using multiple consecutive frames can improve detection of small objects or difficult examples and can improve speed and detection consistency in a video sequence, for instance by interpolating features between frames. In this work, a novel approach is introduced to perform online video object detection using two consecutive frames of video sequences involving road users. Two new models, RetinaNet-Double and RetinaNet-Flow, are proposed, based respectively on the concatenation of a target frame with a preceding frame, and the concatenation of the optical flow with the target frame. The models are trained and evaluated on three public datasets. Experiments show that using a preceding frame improves performance over single frame detectors, but using explicit optical flow usually does not.
Transferring image-based object detectors to the domain of videos remains a challenging problem. Previous efforts mostly exploit optical flow to propagate features across frames, aiming to achieve a good trade-off between accuracy and efficiency. However, introducing an extra model to estimate optical flow can significantly increase the overall model size. The gap between optical flow and high-level features can also hinder it from establishing spatial correspondence accurately. Instead of relying on optical flow, this paper proposes a novel module called Progressive Sparse Local Attention (PSLA), which establishes the spatial correspondence between features across frames in a local region with progressively sparser stride and uses the correspondence to propagate features. Based on PSLA, Recursive Feature Updating (RFU) and Dense Feature Transforming (DenseFT) are proposed to model temporal appearance and enrich feature representation respectively in a novel video object detection framework. Experiments on ImageNet VID show that our method achieves the best accuracy compared to existing methods with smaller model size and acceptable runtime speed.
Various convolutional neural networks (CNNs) were developed recently that achieved accuracy comparable with that of human beings in computer vision tasks such as image recognition, object detection and tracking, etc. Most of these networks, however, process one single frame of image at a time, and may not fully utilize the temporal and contextual correlation typically present in multiple channels of the same image or adjacent frames from a video, thus limiting the achievable throughput. This limitation stems from the fact that existing CNNs operate on deterministic numbers. In this paper, we propose a novel statistical convolutional neural network (SCNN), which extends existing CNN architectures but operates directly on correlated distributions rather than deterministic numbers. By introducing a parameterized canonical model to model correlated data and defining corresponding operations as required for CNN training and inference, we show that SCNN can process multiple frames of correlated images effectively, hence achieving significant speedup over existing CNN models. We use a CNN based video object detection as an example to illustrate the usefulness of the proposed SCNN as a general network model. Experimental results show that even a non-optimized implementation of SCNN can still achieve 178% speedup over existing CNNs with slight accuracy degradation.
In vision-enabled autonomous systems such as robots and autonomous cars, video object detection plays a crucial role, and both its speed and accuracy are important factors to provide reliable operation. The key insight we show in this paper is that speed and accuracy are not necessarily a trade-off when it comes to image scaling. Our results show that re-scaling the image to a lower resolution will sometimes produce better accuracy. Based on this observation, we propose a novel approach, dubbed AdaScale, which adaptively selects the input image scale that improves both accuracy and speed for video object detection. To this end, our results on ImageNet VID and mini YouTube-BoundingBoxes datasets demonstrate 1.3 points and 2.7 points mAP improvement with 1.6x and 1.8x speedup, respectively. Additionally, we improve state-of-the-art video acceleration work by an extra 1.25x speedup with slightly better mAP on ImageNet VID dataset.
Adversarial examples have been demonstrated to threaten many computer vision tasks including object detection. However, the existing attacking methods for object detection have two limitations: poor transferability, which denotes that the generated adversarial examples have low success rate to attack other kinds of detection methods, and high computation cost, which means that they need more time to generate an adversarial image, and therefore are difficult to deal with the video data. To address these issues, we utilize a generative mechanism to obtain the adversarial image and video. In this way, the processing time is reduced. To enhance the transferability, we destroy the feature maps extracted from the feature network, which usually constitutes the basis of object detectors. The proposed method is based on the Generative Adversarial Network (GAN) framework, where we combine the high-level class loss and low-level feature loss to jointly train the adversarial example generator. A series of experiments conducted on PASCAL VOC and ImageNet VID datasets show that our method can efficiently generate image and video adversarial examples, and more importantly, these adversarial examples have better transferability, and thus, are able to simultaneously attack two kinds of representative object detection models: proposal based models like Faster-RCNN, and regression based models like SSD.
Accurate detection and tracking of objects is vital for effective video understanding. In previous work, the two tasks have been combined in a way that tracking is based heavily on detection, but the detection benefits marginally from the tracking. To increase synergy, we propose to more tightly integrate the tasks by conditioning the object detection in the current frame on tracklets computed in prior frames. With this approach, the object detection results not only have high detection responses, but also improved coherence with the existing tracklets. This greater coherence leads to estimated object trajectories that are smoother and more stable than the jittered paths obtained without tracklet-conditioned detection. Over extensive experiments, this approach is shown to achieve state-of-the-art performance in terms of both detection and tracking accuracy, as well as noticeable improvements in tracking stability.
The explosive growth in video streaming gives rise to challenges on performing video understanding at high accuracy and low computation cost. Conventional 2D CNNs are computationally cheap but cannot capture temporal relationships; 3D CNN based methods can achieve good performance but are computationally intensive, making it expensive to deploy. In this paper, we propose a generic and effective Temporal Shift Module (TSM) that enjoys both high efficiency and high performance. Specifically, it can achieve the performance of 3D CNN but maintain 2D CNN's complexity. TSM shifts part of the channels along the temporal dimension; thus facilitate information exchanged among neighboring frames. It can be inserted into 2D CNNs to achieve temporal modeling at zero computation and zero parameters. We also extended TSM to online setting, which enables real-time low-latency online video recognition and video object detection. TSM is accurate and efficient: it ranks the first place on the Something-Something leaderboard upon publication; on Jetson Nano and Galaxy Note8, it achieves a low latency of 13ms and 35ms for online video recognition. The code is available at: https://github.com/mit-han-lab/temporal-shift-module.
State-of-the-art object detectors and trackers are developing fast. Trackers are in general more efficient than detectors but bear the risk of drifting. A question is hence raised -- how to improve the accuracy of video object detection/tracking by utilizing the existing detectors and trackers within a given time budget? A baseline is frame skipping -- detecting every N-th frames and tracking for the frames in between. This baseline, however, is suboptimal since the detection frequency should depend on the tracking quality. To this end, we propose a scheduler network, which determines to detect or track at a certain frame, as a generalization of Siamese trackers. Although being light-weight and simple in structure, the scheduler network is more effective than the frame skipping baselines and flow-based approaches, as validated on ImageNet VID dataset in video object detection/tracking.
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.