An official website of the United States government
Commercial retrospective video analytics platforms have increasingly adopted general interfaces to support the custom queries and convolutional neural networks (CNNs) that different applications require. However, existing optimizations were designed for settings where CNNs were platform- (not user-) determined, and fail to meet at least one of the following key platform goals when that condition is violated: reliable accuracy, low latency, and minimal wasted work. We present Boggart, a system that simultaneously meets all three goals while supporting the generality that today’s platforms seek. Prior to queries being issued, Boggart carefully employs traditional computer vision algorithms to generate indices that are imprecise, but are fundamentally comprehensive across different CNNs/queries. For each issued query, Boggart employs new techniques to quickly characterize the imprecision of its index, and sparingly run CNNs (and propagate results to other frames) in a way that bounds accuracy drops. Our results highlight that Boggart’s improved generality comes at low cost, with speedups that match (and most often, exceed) prior, model-specific approaches.
more »
« less
Focus: Querying Large Video Datasets with Low Latency and Low Cost
Large volumes of videos are continuously recorded from cameras deployed for traffic control and surveillance with the goal of answering “after the fact” queries: identify video frames with objects of certain classes (cars, bags) from many days of recorded video. Current systems for processing such queries on large video datasets incur either high cost at video ingest time or high latency at query time. We present Focus, a system providing both low-cost and low-latency querying on large video datasets. Focus’s architecture flexibly and effectively divides the query processing work between ingest time and query time. At ingest time (on live videos), Focus uses cheap convolutional network classifiers (CNNs) to construct an approximate index of all possible object classes in each frame (to handle queries for any class in the future). At query time, Focus leverages this approximate index to provide low latency, but compensates for the lower accuracy of the cheap CNNs through the judicious use of an expensive CNN. Experiments on commercial video streams show that Focus is 48× (up to 92×) cheaper than using expensive CNNs for ingestion, and provides 125× (up to 607×) lower query latency than a state-of-the-art video querying system (NoScope).
more »
« less
- Award ID(s):
- 1725663
- PAR ID:
- 10136256
- Date Published:
- Journal Name:
- 13th USENIX Symposium on Operating Systems Design and Implementation
- Volume:
- 13
- Page Range / eLocation ID:
- 269-286
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Querying video data has become increasingly popular and useful. Video queries can be complex, ranging from retrieval tasks (“find me the top videos that have … ”), to analytics (“how many videos contained object X per day?”), to excerpting tasks (“highlight and zoom into scenes with object X near object Y”), or combinations thereof. Results for video queries are still typically shown as either relational data or a primitive collection of clickable thumbnails on a web page. Presenting query results in this form is an impedance mismatch with the video medium: they are cumbersome to skim through and are in a different modality and information density compared to the source data. We describe V2V, a system to efficiently synthesize video results for video queries. V2V returns a fully-edited video, allowing the user to consume results in the same manner as the source videos. A key challenge is that synthesizing video results from a collection of videos is computationally intensive, especially within interactive query response times. To address this, V2V features a grammar to express video transformations in a declarative manner and a heuristic optimizer that improves the efficiency of V2V processing in a manner similar to how databases execute relational queries. Experiments show that our V2V optimizer enables video synthesis to run 3x faster.more » « less
-
The constant flux of data and queries alike has been pushing the boundaries of data analysis systems. The increasing size of raw data files has made data loading an expensive operation that delays the data-to-insight time. To alleviate the loading cost, in situ query processing systems operate directly over raw data and offer instant access to data. At the same time, analytical workloads have increasing number of queries. Typically, each query focuses on a constantly shifting—yet small—range. As a result, minimizing the workload latency requires the benefits of indexing in in situ query processing. In this paper, we present an online partitioning and indexing scheme, along with a partitioning and indexing tuner tailored for in situ querying engines. The proposed system design improves query execution time by taking into account user query patterns, to (i) partition raw data files logically and (ii) build lightweight partition-specific indexes for each partition. We build an in situ query engine called Slalom to showcase the impact of our design. Slalom employs adaptive partitioning and builds non-obtrusive indexes in different partitions on-the-fly based on lightweight query access pattern monitoring. As a result of its lightweight nature, Slalom achieves efficient query processing over raw data with minimal memory consumption. Our experimentation with both microbenchmarks and real-life workloads shows that Slalom outperforms state-of-the-art in situ engines and achieves comparable query response times with fully indexed DBMS, offering lower cumulative query execution times for query workloads with increasing size and unpredictable access patterns.more » « less
-
Skyline path queries (SPQs) extend skyline queries to multi-dimensional networks, such as multi-cost road networks (MCRNs). Such queries return a set of non-dominated paths between two given network nodes. Despite the existence of extensive works on evaluating different SPQ variants, SPQ evaluation is still very inefficient due to the nonexistence of efficient index structures to support such queries. Existing index building approaches for supporting shortest-path query execution, when directly extended to support SPQs, use an unreasonable amount of space and time to build, making them impractical for processing large graphs. In this paper, we propose a novel index structure,backbone index, and a corresponding index construction method that condenses an initial MCRN to multiple smaller summarized graphs with different granularity. We present efficient approaches to find approximate solutions to SPQs by utilizing the backbone index structure. Furthermore, considering making good use of historical query and query results, we propose two models,SkylinePathGraphNeuralNetwork (SP-GNN) andTransfer SP-GNN (TSP-GNN), to support effective SPQ processing. Our extensive experiments on real-world large road networks show that the backbone index can support finding meaningful approximate SPQ solutions efficiently. The backbone index can be constructed in a reasonable time, which dramatically outperforms the construction of other types of indexes for road networks. As far as we know, this is the first compact index structure that can support efficient approximate SPQ evaluation on large MCRNs. The results on the SP-GNN and TSP-GNN models also show that both models can help get approximate SPQ answers efficiently.more » « less
-
We consider accelerating machine learning (ML) inference queries on unstructured datasets. Expensive operators such as feature extractors and classifiers are deployed as user-defined functions (UDFs), which are not penetrable with classic query optimization techniques such as predicate push-down. Recent optimization schemes (e.g., Probabilistic Predicates or PP) assume independence among the query predicates, build a proxy model for each predicate offline, and rewrite a new query by injecting these cheap proxy models in the front of the expensive ML UDFs. In such a manner, unlikely inputs that do not satisfy query predicates are filtered early to bypass the ML UDFs. We show that enforcing the independence assumption in this context may result in sub-optimal plans. In this paper, we propose CORE, a query optimizer that better exploits the predicate correlations and accelerates ML inference queries. Our solution builds the proxy models online for a new query and leverages a branch-and-bound search process to reduce the building costs. Results on three real-world text, image and video datasets show that CORE improves the query throughput by up to 63% compared to PP and up to 80% compared to running the queries as it is.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
