scispace - formally typeset
Search or ask a question
Author

Navneet Dalal

Bio: Navneet Dalal is an academic researcher from Google. The author has contributed to research in topics: Object detection & Optical flow. The author has an hindex of 17, co-authored 31 publications receiving 32776 citations. Previous affiliations of Navneet Dalal include Siemens & French Institute for Research in Computer Science and Automation.

Papers
More filters
Patent
28 Dec 2009
TL;DR: In this paper, a user is enabled to specify one or more search criteria that includes image data, and a search result may be determined based on images in the collection that show a corresponding object that has a portion that satisfies a threshold.
Abstract: Embodiments enable searching of portions of objects in images, including programmatically analyzing each image in a collection in order to determine image data that, for individual images in the collection, represents one or more visual characteristics of a portion of an object shown in that image. A user is enabled to specify one or more search criteria that includes image data, and a search result may be determined based on one or more images in the collection that show a corresponding object that has a portion that satisfies a threshold. The threshold is defined at least in part by the one or more search criteria.

233 citations

Patent
13 Jul 2007
TL;DR: In this paper, the retrieved images are analyzed to determine information about an object shown in a corresponding image of the content on display, at least a portion of which is made selectable and associated with the determined information.
Abstract: Images are analyzed by programmatic mechanisms for accessing one or more remote web pages to retrieve content on display at the remote web pages. The retrieved images may be analyzed to determine information about an object shown in a corresponding image of the content on display. At least a portion of the object shown in the corresponding image of the content on display may be made selectable and associated with the determined information. This determined information may subsequently be used, in for example, search applications.

227 citations

Patent
28 Dec 2009
TL;DR: In this article, an image analysis module is used to programmatically analyze individual images in a collection of images in order to determine information about each image in the collection, and a manual interface that is configured to interface with one or more human editors, and displays a plurality of panels concurrently.
Abstract: Embodiments described herein provide for a system for creating a data collection of recognized images. The system includes an image analysis module that is configured to programmatically analyze individual images in a collection of images in order to determine information about each image in the collection. The system may also include a manual interface that is configured to (i) interface with one or more human editors, and (ii) displays a plurality of panels concurrently. Individual panels may be provided for one or more analyzed images, and individual panels may be configured to display information that is at least indicative of the one or more images of that panel and/or of the information determined from the one or more images. Additionally, the manual interface enables the one or more human editors to view the plurality of panels concurrently and to interact with each of the plurality of panels in order to correct or remove any information that is incorrectly determined from the image of that panel.

195 citations

Journal Article
TL;DR: In this article, the authors developed a detector for standing and moving people in videos with possibly moving cameras and backgrounds, testing several different motion coding schemes and showing empirically that orientated histograms of differential optical flow give the best overall performance.
Abstract: Detecting humans in films and videos is a challenging problem owing to the motion of the subjects, the camera and the background and to variations in pose, appearance, clothing, illumination and background clutter. We develop a detector for standing and moving people in videos with possibly moving cameras and backgrounds, testing several different motion coding schemes and showing empirically that orientated histograms of differential optical flow give the best overall performance. These motion-based descriptors are combined with our Histogram of Oriented Gradient appearance descriptors. The resulting detector is tested on several databases including a challenging test set taken from feature films and containing wide ranges of pose, motion and background variations, including moving cameras and backgrounds. We validate our results on two challenging test sets containing more than 4400 human examples. The combined detector reduces the false alarm rate by a factor of 10 relative to the best appearance-based detector, for example giving false alarm rates of 1 per 20,000 windows tested at 8% miss rate on our Test Set 1.

146 citations

Patent
16 Feb 2012
TL;DR: In this paper, an image of a merchandise item is obtained and the image is programmatically analyzed to determine information about the item and the information is used to generate a presentation that includes the item.
Abstract: Embodiments described herein provide a system and method for providing merchandise items at a network site. According to an embodiment, an image of a merchandise item is obtained. The image is programmatically analyzed to determine information about the merchandise item. The information is used to generate a presentation that includes the merchandise item.

129 citations


Cited by
More filters
Proceedings ArticleDOI
07 Jun 2015
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Abstract: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

40,257 citations

Book ChapterDOI
06 Sep 2014
TL;DR: A new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding by gathering images of complex everyday scenes containing common objects in their natural context.
Abstract: We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding. This is achieved by gathering images of complex everyday scenes containing common objects in their natural context. Objects are labeled using per-instance segmentations to aid in precise object localization. Our dataset contains photos of 91 objects types that would be easily recognizable by a 4 year old. With a total of 2.5 million labeled instances in 328k images, the creation of our dataset drew upon extensive crowd worker involvement via novel user interfaces for category detection, instance spotting and instance segmentation. We present a detailed statistical analysis of the dataset in comparison to PASCAL, ImageNet, and SUN. Finally, we provide baseline performance analysis for bounding box and segmentation detection results using a Deformable Parts Model.

30,462 citations

Proceedings ArticleDOI
27 Jun 2016
TL;DR: Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Abstract: We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.

27,256 citations

Proceedings ArticleDOI
23 Jun 2014
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.
Abstract: Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also present experiments that provide insight into what the network learns, revealing a rich hierarchy of image features. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.

21,729 citations

Proceedings ArticleDOI
21 Jul 2017
TL;DR: This paper exploits the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost and achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles.
Abstract: Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But pyramid representations have been avoided in recent object detectors that are based on deep convolutional networks, partially because they are slow to compute and memory intensive. In this paper, we exploit the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost. A top-down architecture with lateral connections is developed for building high-level semantic feature maps at all scales. This architecture, called a Feature Pyramid Network (FPN), shows significant improvement as a generic feature extractor in several applications. Using a basic Faster R-CNN system, our method achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles, surpassing all existing single-model entries including those from the COCO 2016 challenge winners. In addition, our method can run at 5 FPS on a GPU and thus is a practical and accurate solution to multi-scale object detection. Code will be made publicly available.

16,727 citations