Automatic Target Recognition in Infrared Imagery Using Dense HOG Features and Relevance Grouping of Vocabulary

Khan, Mohammad Nazmul Alam; Fan, Guoliang; Heisterkamp, Douglas R.; Yu, Liangjiang

doi:10.1109/cvprw.2014.52

Cited by 30 publications

(19 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On such a scene, feature based tracking methods are adversely affected in the IR spectrum. To overcome this issue of scarcity of discriminative features, overly dense HOG features are used in another context of object recognition [12] with IR images. Such densely sampled HOG features might also be a solution for object tracking, but it would violate the real-time processing requirements of the security and defense applications.…”

Section: Toward Trackers With Superior Ir Performancementioning

confidence: 99%

Comparison of infrared and visible imagery for object tracking: Toward trackers with superior IR performance

Gundogdu

Özkan

Demir

et al. 2015

2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

The subject of this paper is the visual object tracking in infrared (IR) videos. Our contribution is twofold. First, the performance behaviour of the state-of-the-art trackers is investigated via a comparative study using IR-visible band video conjugates, i.e., video pairs captured observing the same scene simultaneously, to identify the IR specific challenges. Second, we propose a novel ensemble based tracking method that is tuned to IR data. The proposed algorithm sequentially constructs and maintains a dynamical ensemble of simple correlators and produces tracking decisions by switching among the ensemble correlators depending on the target appearance in a computationally highly efficient manner. We empirically show that our algorithm significantly outperforms the state-of-the-art trackers in our extensive set of experiments with IR imagery.

show abstract

Section: Toward Trackers With Superior Ir Performancementioning

confidence: 99%

Comparison of infrared and visible imagery for object tracking: Toward trackers with superior IR performance

Gundogdu

Özkan

Demir

et al. 2015

2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

show abstract

“…In [22], a sparse representation-based classification (SRC) algorithm was proposed for infrared target recognition. In [23], the HOG and bag-of-words (BoW) was applied to further improve performance. With respect to the IRCSS, previous methods have finished the detection of targets.…”

Section: Target Recognition and Tracking In Infrared Imagesmentioning

confidence: 99%

Target Recognition in Infrared Circumferential Scanning System via Deep Convolutional Neural Networks

Chen

2020

Sensors

View full text Add to dashboard Cite

With an infrared circumferential scanning system (IRCSS), we can realize long-time surveillance over a large field of view. Recognizing targets in the field of view automatically is a crucial component of improving environmental awareness under the trend of informatization, especially in the defense system. Target recognition consists of two subtasks: detection and identification, corresponding to the position and category of the target, respectively. In this study, we propose a deep convolutional neural network (DCNN)-based method to realize the end-to-end target recognition in the IRCSS. Existing DCNN-based methods require a large annotated dataset for training, while public infrared datasets are mostly used for target tracking. Therefore, we build an infrared target recognition dataset to both overcome the shortage of data and enhance the adaptability of the algorithm in various scenes. We then use data augmentation and exploit the optimal cross-domain transfer learning strategy for network training. In this process, we design the smoother L1 as the loss function in bounding box regression for better localization performance. In the experiments, the proposed method achieved 82.7 mAP, accomplishing the end-to-end infrared target recognition with high effectiveness on accuracy.

show abstract

“…The majority of previous works, e.g. [19] [16], have used IR sensors in a military or surveillance context to detect hot objects, especially during night. From the perspective of a commercial road vehicle, IR sensors have also been used at night to detect other actors such as vehicles and pedestrians [17].…”

Section: Introductionmentioning

confidence: 99%

POL-LWIR Vehicle Detection: Convolutional Neural Networks Meet Polarised Infrared Sensors

Sheeny¹,

Wallace²,

Emambakhsh³

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Figure 1: POL-LWIR Vehicle detection. This paper uses the Thales Catherine MP LWIR sensor, which is based on long wave polarised infrared technology. It contains 4 linear polarisers (0 o , 45 o , 90 o , 135 o ). From the linear polarisers we can compute the Stokes components I,Q,U ,P and φ. Two configurations are created (I,Q,U and I,P ,φ), which are passed to 2 types of neural networks: Faster R-CNN [24] and SSD [22]. The networks are trained to detect vehicles in both day and night conditions. AbstractFor vehicle autonomy, driver assistance and situational awareness, it is necessary to operate at day and night, and in all weather conditions. In particular, long wave infrared (LWIR) sensors that receive predominantly emitted radiation have the capability to operate at night as well as during the day. In this work, we employ a polarised LWIR (POL-LWIR) camera to acquire data from a mobile vehicle, to compare and contrast four different convolutional neural network (CNN) configurations to detect other vehicles in video sequences. We evaluate two distinct and promising approaches, two-stage detection (Faster-RCNN) and one-stage detection (SSD), in four different configurations. We also employ two different image decompositions: the first based on the polarisation ellipse and the second on the Stokes parameters themselves. To evaluate our approach, the experimental trials were quantified by mean average precision (mAP) and processing time, showing a clear trade-off between the two factors. For example, the best mAP result of 80.94 % was achieved using Faster-RCNN, but at a frame rate of 6.4 fps. In contrast, MobileNet SSD achieved only 64.51 % mAP, but at 53.4 fps.

show abstract

Automatic Target Recognition in Infrared Imagery Using Dense HOG Features and Relevance Grouping of Vocabulary

Cited by 30 publications

References 15 publications

Comparison of infrared and visible imagery for object tracking: Toward trackers with superior IR performance

Comparison of infrared and visible imagery for object tracking: Toward trackers with superior IR performance

Target Recognition in Infrared Circumferential Scanning System via Deep Convolutional Neural Networks

POL-LWIR Vehicle Detection: Convolutional Neural Networks Meet Polarised Infrared Sensors

Contact Info

Product

Resources

About